Skip to content

Teradata/jupyter-demos

Repository files navigation


#ClearScape Analytics™ Demonstrations via Jupyter

Welcome to ClearScape Analytics Experience. This service consists of multiple demonstrations of the industry leading in-database analytics that you can run on your own. You can modify them or use them as examples to use with your own tools against our data or small (not sensitive) data you upload. Each notebook will:

  • describe the business situation,
  • will attach the needed data from the cloud, and
  • walk you step-by-step through the use of the ClearScape Analytics functionality.

These are functional demonstrations executed on a tiny platform with small data, but the same functionality is available on all of our platforms up to one with hundreds of nodes and petabytes of data. ClearScape Analytics allows you to apply AI, ML and advanced statistics to your data without the cost and complexity of exporting data. You can develop sophisticated models on other platforms with your favorite tools and import those models to execute in production at massive scale.

If you've never used Jupyter before, we strongly recommend reviewing the First Time User section of Getting Started. You'll find an introduction video with tips on using this platform. There are also tips for you if you just want to look without programming. If you have questions or issues, click here to send an e-mail to ClearScape Analytics Support.


Table of Contents

Items in italics are coming soon.

Getting Started Industries Business Function Analytic Function 3rd Party Tools
First Time User Automotive Finance AWS SageMaker
I am not a programmer Energy & Natural Resources Marketing Azure ML
Developer Information Financial Celebrus
Healthcare Dataiku
Manufacturing H2O.ai
Retail Microsoft PowerBI
Telco MicroStrategy
Travel & Transportation
Defense SAP Business Objects
SAS
Tableau
Vertex AI
AWS Bedrock



Getting Started

First Time User

Getting Started With Azure

Follow these steps to create your first Azure account and create an Azure Machine Learning workspace to complete our AzureML use cases.
Information

Getting Started with Azure OpenAI

Follow these instructions to setup the Azure OpenAI endpoint and generate the access Keys required to run the model.
Python Version

Introduction Video

Video description how to find demos in the index and folder view, tips on running demos and options for foreign vs local tables used in the demonstrations in your ClearScape Analytics environment.
Information

Basic Jupyter Navigation

When running a Jupyter Notebook, there are various indicators that show what is happening. This is a guide to those indicators.
SQL Version

Back to Table of Contents

I am not a programmer

I am not a programmer

Not everyone that uses this site will want to learn programming. Some will want to review the business cases, look at the steps for the analysis and look at the tables, charts and maps. This is a guide for those people.
Information

Back to Table of Contents

Developer Information

Charting and Visualizations using teradataml

The td_plot method streamlines large-scale visualizations by providing users with efficient tools to create visualizations directly within the Vantage platform
Python Version

Data Loading (Python)

Shows how to use python to load CSV data from local storage and from zipped files
Python Version

Data Loading (SQL)

Shows multiple ways to load data from local CSV files, and cloud files on Google and AWS using the SQL kernel.
SQL Version

Query Service REST API

Demonstration of using REST API calls to Vantage which is useful for web or mobile applications to access and maintain data.
Python Version

Using ClearScape Analytics with openAI

To ensure optimal utilization of the OpenAI API in generative AI notebooks, it is essential to establish the API keys correctly. This concise guide outlines the process of configuring OpenAI API keys for seamless integration across multiple notebooks.
Information

Convert PySpark to teradatamlspk

Convert a PySpark script to teradatamlspk syntax and generate a HTML report using Housing Prices to generate price predictions.
Python Version

tdplyr R Basics

Work through using the bgasics of the Teradata R package, tdplyr
R Version

Vantage Query Log Analysis

Analysis of sessions and queries you executed using the built-in logging facilities of Vantage.
SQL Version

Data Loading ('R')

Shows multiple ways to load data from local CSV files, and cloud files on Google and AWS using the SQL kernel.
R Version

Execute Custom Python Scripts in Vantage

Run an external custom python script in Vantage using Script Table Operator(STO) to execute custom python scripts on Vantage
Python Version

Tutorial on using Teradataml Widgets

Use Teradataml Widgets to display interactive prompting to generate datasets from the Vantage database.
Python Version

Introduction to Plot types using Teradataml Widgets.

This is an introduction to using the various Plot types available as widgets: Line, Bar, Mesh, Wiggle, Geometry, etc.
Python Version

Teradata Package for R Basics

Discoverer how the Teradata Package for R (tdplyr) allows users to develop and run R programs to take advantage of Big Data and Machine Learning analytic capabilities of Vantage.
Information

Initiate Parallel CPU Inferencing of Hugging Face Models in Vantage

Execute this notebook first to prepare the environment to demonstrate Parallel CPU Inferencing of Hugging Face Models in Vantage
Python Version

SQL Basics in Jupyter

This guide will walk you through writing your first SQL queries in Jupyter. It uses some of the Vantage system tables as a source for the queries.
SQL Version

teradataml Python Basics

Introduction to Teradataml package for Python including connecting to Vantage, Teradata DataFrames, data manipulation and export to Pandas.
Python Version

Intro to Panda for Python

Provides step-by-step instructions on the basics of using Python Pandas with Jupyter notebooks.
Python Version

Charting and Visualization

Data from queries is brought to life with graphics and charts. This shows how to use the %chart magic command to display results.
SQL Version

VAL Overview

Vantage Analytics Library (VAL) is a set of over 50 functions for advanced analytics. This provides an overview and links to an 8 minute video overview.
SQL Version

Data Dictionary

This provides an index to all of the databases used by demo notebooks on this machine, allowing you to use that data for your own notebooks or BI tools.
Python Version

How to Submit Your Demos

It is very easy to submit your demo for publication. Tell us directory with the notebook and referenced files and grant us access to your database. We'll take it from there.
Python VersionVideo

Back to Table of Contents


Industries

Automotive

Anomaly Detection

Evaluates potential failures in spot welds based on voltage anomalies during the welding process.
Python-SQL VersionVideo

Battery Defect Analysis

Uses local data (or foreign tables on GCP) to analyze patterns of battery failure, then links to data on AWS for detailed battery measurement.
Python Version

Car Complaints

Uses geospatial techniques to locate service centers close to the complaint and outlier detection to detect part defects earlier than expected.
Python-SQL Version

Back to Table of Contents

Energy & Natural Resources

Carbon Footprint Analytics

A key component of ESG is Carbon Footprint. This demonstrates a part of a solution available from Teradata to integrate multiple data sources to calculate carbon footprint of various corporate activities.
Python-SQL Version

Energy Consumption Forecasting

This combines machine learning and BYOM to forecast energy consumption using Vantage to score the model at scale without having to export all data.
Python Version

Energy Consumption Forecasting Dataiku

Demonstration of using Dataiku with Vantage. Instructions provided for use with your Dataiku copy + screen shots if you don't have Dataiku. PMML model from Dataiku is imported to Vantage for execution and scoring.
Python Version

Energy Consumption Forecasting using AzureML

This leverages the power of AzureML and Teradata Vantage to enhance our machine learning capabilities and enable scalable model scoring to forecast energy consumption.
Python Version

Flood Proximity to Climate Risk Analysis

This allows enterprises to rapidly analyze this geographic-related information in real-time at any scale - effectively understanding the impacts of these climate events on entire populations.
Python Version

Back to Table of Contents

Financial

Anomaly Detection of Outstanding Amounts

Anomaly detection in bank accounts can help in identifying unusual patterns, potentially flagging issues like errors or fraudulent activities. Enterprise re-use of Features ensures rapid creation & deployment of models while new Features can be created and used without extensive engineering support.
Python Version

Credit Card Data Preparation

Uses functions from TeradataML Python library to prepare data for analysis using data cleansing, exploration and feature engineering functions.
Python Version

Mortgage Calculator using GenAI

Use Retrieval-Augmented Generation (RAG), Lanchain and LLM models to as questions about loans and retrieve relevant data from Vantage.
Python Version

Banking Customer Churn

Uses a combination of Vantage Analytics Library to prepare data, using machine learning in python and importing the resulting PMML model into Vantage for scoring.
Python Version

Cash Demand Forecasing

Predicts the future demand for cast in Automatic Teller Machines (ATMs) using Auto Regressive Integrated Moving Average (ARIMA) using In-Database functions.
SQL Version

Consumer Complaints

Uses government consumer complaint data with SQL queries and visualizations to identify source of top complaints.
SQL Version

Credit Card Data Preparation

This shows the use of ClearScape analytics to reduce the pre-processing effort of incoming raw credit card data to prepare for analysis of potential loan defaulters.
SQL Version

Digital Identity Management

Combines ClearScape Analytics with Celebrus to track unique customers across web sessions and devices to drive personalized experiences
SQL Version

Financial Customer Journey

Uses analytic techniques to find new customers, measure marketing attribution, and maximizing marketing effectiveness
Python-SQL VersionSQL VersionVideo

Financial Fraud Detection InDB

Detect financial transaction fraud using powerful in-database machine learning functions
Python VersionVideo

Financial Fraud Detection VIA BYOM

A model that was developed externally is imported into Vantage for evaluation and execution at scale to detect fraud.
Python Version

Flood Proximity to Climate Risk Analysis

This allows enterprises to rapidly analyze this geographic-related information in real-time at any scale - effectively understanding the impacts of these climate events on entire populations.
Python Version

Insurance Policy Temporal

Show As-IS/As-Was capabilities of Vantage Temporal to dramatically simplify the SQL and improve performance for analyzing insurance policies versus claims.
SQL Version

Credit Risk Assessment using Teradataml OpenSource Functions

Use inDb functions with OpensourceML to create multiple DecisionTreeClassifiers to create multiple predictions of a Credit Risk Assessment.
Python Version

Financial Fraud Detection InDB

Detect financial transaction fraud using powerful in-database machine learning functions
Python VersionR Version

Mortgage Calculator Chatbot using GenAI: Finetune LLM

Fine-tuned an OpenAI model using RAG, LangChain and LLM models framework. Query a chatbot for answers about a mortgage and available housing within a predefiend area.
Python Version

Mortgage Calculator chatbot using GenAI: RAG

Build a conversational chatbot and ask questions about a mortgage and available housing within a predefined area using LangChain.
Python Version

Mortgage Calculator Chatbot using Trusted AI(RAG)

Experience the integration of LLM models to provide user-friendly responses to queries. RAG combines retrieval and generative approaches.
Python Version

Banking Churn Prediction with AutoML

Implement the entire lifecycle of churn prediction using BYOM, VAL and AutoML.
Python Version

Back to Table of Contents

Healthcare

Data Science 101 with Python

This walks through the Cross-Industry Standard Process for Data Mining (CRISP-DM) from data understanding through modeling and evaluation.
Python Version

Diabetes Prediction via BYOM H2O

This uses BYOM to import a trained H2O model to identify potential diabetes patients. BYOM allows the data scientist to create models in languages they prefer and run at scale inside Vantage without moving data.
Python-SQL Version

Diabetes Prediction via DF and GLM

Decision Forest and Generalized Linear Model are applied to identify factors that indicate diabetes. The earlier the disease is identified, the better the chance of reducing organ damage.
Python Version

Heart Failure Prediction

Machine learning is applied to the complex attributes of patients to help recognize patterns that may lead to heart failure faster than a human may recognize.
Python-SQL Version

Knee Replacement Attribution

The ClearScape Analytics Attribution function is used to determine the weight of various events that precede the final outcome, in this example, knee replacement.
SQL Version

Knee Replacement nPath

This uses the ClearScape Analytics nPath® function to provide visuals on the events leading up to the final outcome, in this case, knee replacement.
Python Version

Cancer Prediction using the TDAPIClient and VertexAI

Use TDAPIClient to connect to the Google Cloud Vertex API Endpoint to orchestrate Extreme Gradient XG Boost model training and score the model in SageMaker. Deploy the solution's ML model.
Python Version

Mental Health Chat with Fine-tuned OpenAI Model

Train a GPT-3.5 Turbo model using the OpenAI API endpoint. Ask mental health questions using a chat input box.
Python Version

Parkinson's Disease Prediction using Signal Processing

Detect Parkinson's Disease at an early stage by using Vantage InDB functions for model training and scoring to compare the performance of two models against biomedical voice measurements.
Python Version

Predicting Medical Expenses in Healthcare

Use a dataset containing variables like age, sex, BMI, smoking status, number of children, and region to build machine learning models that accurately predict healthcare costs for insurance policyholders, taking into account factors that affect medical expenses.
Python Version

Cancer Prediction using Teradata and the SageMaker API

Use the Vantage SageMaker API feature to connect to an Amazon Endpoint to orchestrate Extreme Gradient XG Boost model training and score the model in SageMaker. Deploy the solution's ML model.
Python Version

Back to Table of Contents

Manufacturing

Anomaly Detection

Evaluates potential failures in spot welds based on voltage anomalies during the welding process.
Python-SQL VersionVideo

Battery Defect Analysis

Uses local data (or foreign tables on GCP) to analyze patterns of battery failure, then links to data on AWS for detailed battery measurement.
Python Version

Car Complaints

Uses geospatial techniques to locate service centers close to the complaint and outlier detection to detect part defects earlier than expected.
Python-SQL Version

Green Manufacturing

Uses analytic and ML techniques to predict how long vehicle testing will take based on combination of features installed.
Python Version

Predictive Maintenance

Uses ML functions to predict failures to identify and mitigate potential machine failures before they occur.
Python-SQL Version

Remaining Useful Life Forecasting

Applies machine learning to predict Remaining Useful Life (RUL) of jet engines, allowing scheduling of maintenance and replacement before failure occurs and reduces the cost of maintenance and replacement.
Python-SQL Version

Anomaly Detection in Spot Welding Process - Trusted AI

Evaluates potential failures in spot welds based on voltage anomalies during the welding process.
Python Version

Back to Table of Contents

Retail

Product Recommentations via TDApiClient

Build a product recommendation system using OpenAI embeddings and Vantage in db_function VectorDistance. We will also use Vantage as VectorDB, to store the embeddings.
Python Version

Broken Digital Journey

This uses nPath® analysis to show the retail events that prevent the ultimate objective: a purchase. This uses interactive Sankey diagrams to understand the problems.
Python VersionVideo

Competitor Proximity Geospatial Analysis

This looks at the impact on purchasing when people that shop at our stores live within reasonable drive time to a competitor. This could identify proximity based marketing tactics to target larger promotions to those customers to increase share of their spend.
Python Version

Customer Behavior Analysis

Analysis of customer purchase behavior using nPath® analysis in Python with visualization using Sankey diagrams.
Python VersionSQL Version

Deep History via Object Store

This demonstrates integration of local data or foreign tables on GCP and integration across cloud providers to detailed historical sales records on AWS.
SQL Version

Hyper-Personalization

Hyper-personalization creates models from customer iteractions on multiple channels to determine the "Next Best Offer" for the individual.
Python-SQL Version

K-Means Clustering and ML model

This uses the unsupervised K-Means ML algorithm to identify patterns in retail purchases.
SQL Version

Marketing Campaign Effectiveness

Examines the results of campaigns by various customer attributes then uses correlation, outlier elimination, and machine learning to identify the best campaigns.
Python-SQL Version

Multi-Touch Attribution for Business Analyst

This version of the Multi-Touch Attribution demonstration is focused on the interests of the Business Analyst.
Python-SQL Version

Multi-Touch Attribution for Data Scientist

Demonstrates attribution of customer behavior via single touch and multi-touch rule-based models using statistical and algorithmic models. Multiple approaches are demonstrated.
Python-SQL Version

Product Recommendations via Open Source

Uses FlagEmbedding from HuggingFace plus Vantage in-database functions to assess the vector distance between the product entered and similar products.
Python Version

Product Recommendations via OpenAI

Uses OpenAIEmbeddings and Vantage in-database function to assists consumers in receiving product recommendations
Python Version

Retail Demand Forecasting

This creates an ARIMA time series model based on holidays and merchandising activities impacting store sales for a hypermarket retailer.
Python Version

Sales Forecasting using UAF

A detailed coverage of the analytic steps in sales forecasting including data preparation, exploration, seasonal normalizing, model creation, validation, and forecasting.
Python Version

Store Sales Forecast via ARIMA

Forecasts total store sales using ARIMA (AutoRegressive Integrated Moving Average)
Python Version

Store Sales Forecast via Prophet

Uses the Script Table Operator (STO) to run the H20 machine learning library as an extension to ClearScape Analytics. H20 runs in parallel inside the Vantage database without exporting data to another platform.
Python-SQL Version

Text Term Frequency

Use NGram splitter to analyze comments retail products to determine patterns of words used to describe products.
Python VersionPython-SQL VersionSQL Version

Customer Reviews Analysis using GenAI

Customer reviews analysis is a crucial aspect of understanding customer sentiment and preferences. By leveraging the power of OpenAIEmbeddings and Vantage InDB Analytic Function, we can gain valuable insights from customer reviews.
Python Version

Product Recommendation via AWS Bedrock

Use AWS Bedrock, Embedding from HuggingFace and Vantage in-DB functions to assist in providing product recommendations to develop a recipe assistant chatbot.
Python Version

Natural Language Processing

Use NLP for Sentiment Analysis, perform Kmeans clustering, execute Principal Component Analysis (PCA) using comments received by a Retail Store
Python-SQL Version

Enhance Product Hierarchies with In-DB K-means Clustering

Enhance a product hierarchy by leveraging time series analysis and clustering techniques
Python Version

Generate Teradata SQL with GenAI and AWS Bedrock

In this demo, we use AWS Bedrock's LLMs and LangChain to create a text-to-Teradata SQL agent.
Python Version

Sales Forecasting using Teradata AUTOARIMA

Forecast the amount of future sales by developing a time-series modelling pipeline using Vantage and In-DB analytics
Python Version

Back to Table of Contents

Telco

Telco 5G Quality of Experience

Quality of service analysis of 5G vs 4G video for different situations such as Indoor, outdoor, and moble.
SQL Version

Graph Analysis of CDR Records

Uses graph analysis to identify communities and key influencers within Call Data Records. This uses Script Table Operator to invoke external procedures to work inside the Vantage database without exporting data.
Python-SQL Version

Telco Customer Churn

This uses logistic regression for supervised learning to predict the probability of a customer switching vendors based on usage patterns, billing information demographics and interactions. XGBoost is then used in database to improve the prediction.
Python VersionVideo

Telco Network Coverage

Demonstrates the ability of Geospatial to show signal strength, coverage areas and travel path of customers through cell tower coverage area.
Python Version

Back to Table of Contents

Travel & Transportation

Chatbot using GenAI with insurance PDF document

Uses TD_VectorDistance in Vantage to create a chatbot using Retrieval-Augmented Generation (RAG), Langchain, and LLM to answer questions using a 24 page travelers insurance policy PDF as source data to answer questions about coverage.
Python VersionPython-SQL Version

Shipping Time Prediction

Use ClearScape Analytics to develop a robust system that can reliably estimate delivery dates, accounting for handling time, transit time, and other relevant variables affecting the actual delivery timeframe.
Python-SQL Version

Supply Chain Visibility

Shows the integration of data from warehouse, trucking company, and customer Order Management Systems (OMS) using temporal to reconcile different update frequencies and show rerouting when warehouse is unavailable.
Python Version

Vehicle Routing for Delivery

Demonstrates advanced analytics to find lowest cost routes to deliver a large volume of packages by a fleet of vehicles.
Python-SQL Version

4D Analytics on bike sharing

Demonstration of Geospatial and TimeSeries using Austin bike trip data between 2014 and 2017.
Python-SQL VersionSQL Version

Air Passenger Forecasting

Applies Auto Regressive Integrated Moving Average (ARIMA) analysis to forecast airplane passenger volume.
SQL Version

NYC Taxi Geospatial

Applies geospatial functions to analysis of NYC Taxi pickups and drop off locations.
Python-SQL Version

Remaining Useful Life Forecasting

Applies machine learning to predict Remaining Useful Life (RUL) of jet engines, allowing scheduling of maintenance and replacement before failure occurs and reduces the cost of maintenance and replacement.
Python-SQL Version

Train Delay Path Analysis

Uses nPath displays to show relationship of delays and predictive models to anticipate potential delays and enable proactive planning.
Python Version

Back to Table of Contents

Defense

Signal Processing and Classification

Use the Unbounded Array Framework in ClearScape Analytics to classify sonar signals. Extract and engineer features to use in training and scoring our models.
Python Version

Back to Table of Contents


Business Function

Marketing

Competitor Proximity Geospatial Analysis

This looks at the impact on purchasing when people that shop at our stores live within reasonable drive time to a competitor. This could identify proximity based marketing tactics to target larger promotions to those customers to increase share of their spend.
Python Version

Customer 360

This integrates data about customers from multiple sources using multiple matching techniquest to create the "Golden Customer Record" and calculate LTV.
SQL Version

Digital Identity Management

Combines ClearScape Analytics with Celebrus to track unique customers across web sessions and devices to drive personalized experiences
SQL Version

Generative AI Question Answering

Uses OpenAI to translate english language questions into SQL queries to run against a table of marketing data. This includes a link to a notebook with instructions for getting the required OpenAI API key.
Python VersionVideo

Hyper-Personalization

Hyper-personalization creates models from customer iteractions on multiple channels to determine the "Next Best Offer" for the individual.
Python-SQL Version

Marketing Campaign Effectiveness

Examines the results of campaigns by various customer attributes then uses correlation, outlier elimination, and machine learning to identify the best campaigns.
Python-SQL Version

Multi-Touch Attribution for Business Analyst

This version of the Multi-Touch Attribution demonstration is focused on the interests of the Business Analyst.
Python-SQL Version

Multi-Touch Attribution for Data Scientist

Demonstrates attribution of customer behavior via single touch and multi-touch rule-based models using statistical and algorithmic models. Multiple approaches are demonstrated.
Python-SQL Version

Store Sales Forecast via ARIMA

Forecasts total store sales using ARIMA (AutoRegressive Integrated Moving Average)
Python Version

Back to Table of Contents


Analytic Function

Arima

Sales Forecasting using Teradata AUTOARIMA

Forecast the amount of future sales by developing a time-series modelling pipeline using Vantage and In-DB analytics
Python Version

Back to Table of Contents

Aspect-Based Sentiment Analysis

Insights from Sentiment Analysis with AWS Bedrock

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Sentiment Analysis with Google Gemini

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Back to Table of Contents

AutoML

Banking Churn Prediction with AutoML

Implement the entire lifecycle of churn prediction using BYOM, VAL and AutoML.
Python Version

Back to Table of Contents

Complaint Summarization

Complaints Classification with AWS Bedrock

Classify customer complaints to swiftly identify and address concerns.
Python Version

Complaints Summarization with AWS Bedrock

Efficiently manage and analyze customer complaints, providing actionable insights to enhance customer satisfaction and improve business operations.
Python Version

Back to Table of Contents

Complaints Classification

Complaints Classification with Google Gemini

Classify customer complaints to swiftly identify and address concerns.
Python Version

Back to Table of Contents

Complaint Summarization

Complaints Summarization with Google Gemini

Efficiently manage and analyze customer complaints, providing actionable insights to enhance customer satisfaction and improve business operations.
Python Version

Back to Table of Contents

Complaints Classification

Complaints Classification with OpenAI

Classify customer complaints to swiftly identify and address concerns.
Python Version

Back to Table of Contents

Complaint Summarization

Complaints Summarization with OpenAI

Efficiently manage and analyze customer complaints, providing actionable insights to enhance customer satisfaction and improve business operations.
Python Version

Customer Complaints Analysis with Customer360 with Google Gemini

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Back to Table of Contents

Complaints Clustering

Complaints Clustering with AWS Bedrock

Use advanced clustering techniques using AI Embeddings model to group similar customer complaints together.
Python Version

Semantic Clustering using OpenSource Language Models

Bring a language model into Vantage and run NLP models in the database
Python Version

Complaints Clustering with Google Gemini

Use advanced clustering techniques using AI Embeddings model to group similar customer complaints together.
Python Version

Complaints Clustering with OpenAI

Use advanced clustering techniques using AI Embeddings model to group similar customer complaints together.
Python Version

Back to Table of Contents

Customer 360

Customer Complaints Analysis with Customer360 with AWS Bedrock

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Customer Complaints Analysis with Customer360 with Google Gemini

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Customer Complaints Analysis with Customer360 with OpenAI

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Back to Table of Contents

Data Preparation

Credit Card Data Preparation

Uses functions from TeradataML Python library to prepare data for analysis using data cleansing, exploration and feature engineering functions.
Python VersionSQL Version

Data Prep and Transformation

This demonstrates a subset of the over 100 analytic functions in the teradataml package for Python
Python VersionPython-SQL Version

Outlier Analysis

Outliers in an analysis skew the results and make it difficult to recognize the main patterns. ClearScape Analytics has tools to remove outliers automatically.
SQL Version

Sales Forecasting using UAF

A detailed coverage of the analytic steps in sales forecasting including data preparation, exploration, seasonal normalizing, model creation, validation, and forecasting.
Python Version

Data Loading ('R')

Shows multiple ways to load data from local CSV files, and cloud files on Google and AWS using the SQL kernel.
R Version

Predicting Medical Expenses in Healthcare

Use a dataset containing variables like age, sex, BMI, smoking status, number of children, and region to build machine learning models that accurately predict healthcare costs for insurance policyholders, taking into account factors that affect medical expenses.
Python Version

Back to Table of Contents

Descriptive Statistics

Sales Forecasting using UAF

A detailed coverage of the analytic steps in sales forecasting including data preparation, exploration, seasonal normalizing, model creation, validation, and forecasting.
Python Version

VAL Descriptive Statistics

This performs in-database analysis of data values, distribution, histograms, and text field analysis using SQL to access the Vantage Analytics Library.
SQL Version

VAL teradataml Demo

Demonstrated the use of Teradataml in Python to perform descriptive statistics, transformation, model building model evaluation and scoring.
Python Version

Back to Table of Contents

Emotion Detection

Insights from Sentiment Analysis with AWS Bedrock

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Sentiment Analysis with Google Gemini

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Back to Table of Contents

Fraud Detection

Financial Fraud Detection InDB

Detect financial transaction fraud using powerful in-database machine learning functions
Python VersionR Version

Back to Table of Contents

Generative AI

Chatbot using GenAI with insurance PDF document

Uses TD_VectorDistance in Vantage to create a chatbot using Retrieval-Augmented Generation (RAG), Langchain, and LLM to answer questions using a 24 page travelers insurance policy PDF as source data to answer questions about coverage.
Python VersionPython-SQL Version

Mortgage Calculator using GenAI

Use Retrieval-Augmented Generation (RAG), Lanchain and LLM models to as questions about loans and retrieve relevant data from Vantage.
Python Version

Product Recommentations via TDApiClient

Build a product recommendation system using OpenAI embeddings and Vantage in db_function VectorDistance. We will also use Vantage as VectorDB, to store the embeddings.
Python Version

Generative AI Question Answering

Uses OpenAI to translate english language questions into SQL queries to run against a table of marketing data. This includes a link to a notebook with instructions for getting the required OpenAI API key.
Python VersionVideo

Product Recommendations via Open Source

Uses FlagEmbedding from HuggingFace plus Vantage in-database functions to assess the vector distance between the product entered and similar products.
Python Version

Product Recommendations via OpenAI

Uses OpenAIEmbeddings and Vantage in-database function to assists consumers in receiving product recommendations
Python Version

Complaints Classification with OpenAI

Classify customer complaints to swiftly identify and address concerns.
Python Version

Complaints Clustering with OpenAI

Use advanced clustering techniques using AI Embeddings model to group similar customer complaints together.
Python Version

Complaints Summarization with OpenAI

Efficiently manage and analyze customer complaints, providing actionable insights to enhance customer satisfaction and improve business operations.
Python Version

Customer Complaints Analysis with Customer360 with OpenAI

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Generate Teradata SQL with GenAI and AWS Bedrock

In this demo, we use AWS Bedrock's LLMs and LangChain to create a text-to-Teradata SQL agent.
Python Version

Sentiment Analysis with OpenAI

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Speech Recognition and Sentiment Analysis with OpenAI

Analyzing consumer complaints using audio files conversations
Python Version

Topic Modelling with OpenAI

Uncover hidden insights from vast amounts of consumer complaints data to enable the identification of trends.
Python Version

Customer Reviews Analysis using GenAI

Customer reviews analysis is a crucial aspect of understanding customer sentiment and preferences. By leveraging the power of OpenAIEmbeddings and Vantage InDB Analytic Function, we can gain valuable insights from customer reviews.
Python Version

Grocery Recommendations using GenAI

Use context-based product recommendations powered by GenAI Large Language Models to enhance a shopping experience.
Python-SQL Version

Mortgage Calculator Chatbot using Trusted AI(RAG)

Experience the integration of LLM models to provide user-friendly responses to queries. RAG combines retrieval and generative approaches.
Python Version

Product Recommendation via AWS Bedrock

Use AWS Bedrock, Embedding from HuggingFace and Vantage in-DB functions to assist in providing product recommendations to develop a recipe assistant chatbot.
Python Version

Mortgage Calculator Chatbot using GenAI: Finetune LLM

Fine-tuned an OpenAI model using RAG, LangChain and LLM models framework. Query a chatbot for answers about a mortgage and available housing within a predefiend area.
Python Version

Mortgage Calculator chatbot using GenAI: RAG

Build a conversational chatbot and ask questions about a mortgage and available housing within a predefined area using LangChain.
Python Version

Complaints Clustering with Google Gemini

Use advanced clustering techniques using AI Embeddings model to group similar customer complaints together.
Python Version

Back to Table of Contents

Geospatial

Supply Chain Visibility

Shows the integration of data from warehouse, trucking company, and customer Order Management Systems (OMS) using temporal to reconcile different update frequencies and show rerouting when warehouse is unavailable.
Python Version

4D Analytics on bike sharing

Demonstration of Geospatial and TimeSeries using Austin bike trip data between 2014 and 2017.
Python-SQL VersionSQL Version

Car Complaints

Uses geospatial techniques to locate service centers close to the complaint and outlier detection to detect part defects earlier than expected.
Python-SQL Version

Competitor Proximity Geospatial Analysis

This looks at the impact on purchasing when people that shop at our stores live within reasonable drive time to a competitor. This could identify proximity based marketing tactics to target larger promotions to those customers to increase share of their spend.
Python Version

Flood Proximity to Climate Risk Analysis

This allows enterprises to rapidly analyze this geographic-related information in real-time at any scale - effectively understanding the impacts of these climate events on entire populations.
Python Version

NYC Taxi Geospatial

Applies geospatial functions to analysis of NYC Taxi pickups and drop off locations.
Python-SQL Version

Sensor Data Analytics

Creative application of geospatial to locations of sensors in a research lab and integration of data from tables with detailed recordings on cloud storage.
Python-SQL Version

Telco Network Coverage

Demonstrates the ability of Geospatial to show signal strength, coverage areas and travel path of customers through cell tower coverage area.
Python Version

Back to Table of Contents

Hyperparameter Tuning

Hyperparameter Tuning using the Titanic Passenger Dataset

Create a predictive algorithm that can identify whethr or not passengers on the Titanic survived the ship's sinking.
Python Version

Back to Table of Contents

Hypothesis testing

Competitor Proximity Geospatial Analysis

This looks at the impact on purchasing when people that shop at our stores live within reasonable drive time to a competitor. This could identify proximity based marketing tactics to target larger promotions to those customers to increase share of their spend.
Python Version

Data Science 101 with Python

This walks through the Cross-Industry Standard Process for Data Mining (CRISP-DM) from data understanding through modeling and evaluation.
Python Version

Sales Forecasting using UAF

A detailed coverage of the analytic steps in sales forecasting including data preparation, exploration, seasonal normalizing, model creation, validation, and forecasting.
Python Version

VAL Hypothesis Tests

This demonstrates a subset of the 18 hypothesis test in the Vantage Analytics library using SQL such as Parametric, Binomial, Kolmogorov/Smirnoff, Rank, etc.
SQL Version

Back to Table of Contents

Language Models

Initiate Parallel CPU Inferencing of Hugging Face Models in Vantage

Execute this notebook first to prepare the environment to demonstrate Parallel CPU Inferencing of Hugging Face Models in Vantage
Python Version

Streamlining Analytics with Hyper-Segmented Models

By addressing unique customer behaviors and preferences within specific micro-segments, enhance customer satisfaction, boost operational efficiency, and improve profitability by to deploying and managing hyper-segmented models at scale.
Python Version

RAG Solution with Embedding/Chunking with Vantage and AWS Bedrock

Chunk PDFs, run embedding, try vector db style indexing in Vantage and then query Language Model with context/prompts after semantic search
Python Version

RAG Solution with Vantage Model Catalog and AWS Bedrock

Explore how to do extract data from metadata tables of Teradata using embedding and vector db style indexing in Vantage and then query LLM with context/prompts to get the details
Python Version

Semantic Clustering using OpenSource Language Models

Bring a language model into Vantage and run NLP models in the database
Python Version

Semantic Similarity using OpenSource Language Models

Run Hugging Face Embedding Model in ONNX format to create some embeddings from a Consumer Complaints dataset
Python Version

Back to Table of Contents

Large Language Models

Complaints Classification with OpenAI

Classify customer complaints to swiftly identify and address concerns.
Python Version

Complaints Clustering with OpenAI

Use advanced clustering techniques using AI Embeddings model to group similar customer complaints together.
Python Version

Complaints Summarization with OpenAI

Efficiently manage and analyze customer complaints, providing actionable insights to enhance customer satisfaction and improve business operations.
Python Version

Customer Complaints Analysis with Customer360 with OpenAI

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Sentiment Analysis with OpenAI

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Speech Recognition and Sentiment Analysis with AWS Bedrock

Analyzing consumer complaints using audio files conversations
Python Version

Speech Recognition and Sentiment Analysis with OpenAI

Analyzing consumer complaints using audio files conversations
Python Version

Topic Modelling with OpenAI

Uncover hidden insights from vast amounts of consumer complaints data to enable the identification of trends.
Python Version

Complaints Summarization with AWS Bedrock

Efficiently manage and analyze customer complaints, providing actionable insights to enhance customer satisfaction and improve business operations.
Python Version

Complaints Classification with Google Gemini

Classify customer complaints to swiftly identify and address concerns.
Python Version

Complaints Clustering with Google Gemini

Use advanced clustering techniques using AI Embeddings model to group similar customer complaints together.
Python Version

Complaints Summarization with Google Gemini

Efficiently manage and analyze customer complaints, providing actionable insights to enhance customer satisfaction and improve business operations.
Python Version

Customer Complaints Analysis with Customer360 with Google Gemini

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Sentiment Analysis with Google Gemini

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Speech Recognition and Sentiment Analysis with Google Gemini

Analyzing consumer complaints using audio files conversations
Python Version

Topic Modelling with Google Gemini

Uncover hidden insights from vast amounts of consumer complaints data to enable the identification of trends.
Python Version

Complaints Clustering with AWS Bedrock

Use advanced clustering techniques using AI Embeddings model to group similar customer complaints together.
Python Version

Topic Modelling with AWS Bedrock

Uncover hidden insights from vast amounts of consumer complaints data to enable the identification of trends.
Python Version

Customer Complaints Analysis with Customer360 with AWS Bedrock

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Insights from Sentiment Analysis with AWS Bedrock

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Customer Complaints Analysis Dashboard with OpenAI

This is a Dashboard with descriptions and links to various notebooks on various topics using Teradata Vantage and Microsoft Azure.
Information

Customer Complaint Analysis with Google Gemini

This is a Dashboard with descriptions and links to various notebooks on various topics using Teradata Vantage and Google Gemini.
Information

Customer Complaint Analysis with AWS Bedrock

This is a collection of demos showing multiple methods of dealing with customer complaints using various GenAI techniques.
Information

Back to Table of Contents

Machine learning

Anomaly Detection of Outstanding Amounts

Anomaly detection in bank accounts can help in identifying unusual patterns, potentially flagging issues like errors or fraudulent activities. Enterprise re-use of Features ensures rapid creation & deployment of models while new Features can be created and used without extensive engineering support.
Python Version

Sales Forecasting with Vantage vs SAS

This demo walks through how a typical SAS user would use sales data to build a simple sales forecasting model and then will showcase how we can achieve the same using Vantage ClearScape Analytics.
Python-SQL VersionSQL Version

Shipping Time Prediction

Use ClearScape Analytics to develop a robust system that can reliably estimate delivery dates, accounting for handling time, transit time, and other relevant variables affecting the actual delivery timeframe.
Python-SQL Version

Telco 5G Quality of Experience

Quality of service analysis of 5G vs 4G video for different situations such as Indoor, outdoor, and moble.
SQL Version

Anomaly Detection

Evaluates potential failures in spot welds based on voltage anomalies during the welding process.
Python-SQL VersionVideo

Banking Customer Churn

Uses a combination of Vantage Analytics Library to prepare data, using machine learning in python and importing the resulting PMML model into Vantage for scoring.
Python Version

Diabetes Prediction via DF and GLM

Decision Forest and Generalized Linear Model are applied to identify factors that indicate diabetes. The earlier the disease is identified, the better the chance of reducing organ damage.
Python Version

Financial Fraud Detection InDB

Detect financial transaction fraud using powerful in-database machine learning functions
Python VersionVideo

Financial Fraud Detection VIA BYOM

A model that was developed externally is imported into Vantage for evaluation and execution at scale to detect fraud.
Python Version

Graph Analysis of CDR Records

Uses graph analysis to identify communities and key influencers within Call Data Records. This uses Script Table Operator to invoke external procedures to work inside the Vantage database without exporting data.
Python-SQL Version

Green Manufacturing

Uses analytic and ML techniques to predict how long vehicle testing will take based on combination of features installed.
Python Version

Heart Failure Prediction

Machine learning is applied to the complex attributes of patients to help recognize patterns that may lead to heart failure faster than a human may recognize.
Python-SQL Version

Hyper-Personalization

Hyper-personalization creates models from customer iteractions on multiple channels to determine the "Next Best Offer" for the individual.
Python-SQL Version

K-Means Clustering and ML model

This uses the unsupervised K-Means ML algorithm to identify patterns in retail purchases.
SQL Version

Marketing Campaign Effectiveness

Examines the results of campaigns by various customer attributes then uses correlation, outlier elimination, and machine learning to identify the best campaigns.
Python-SQL Version

Multi-Touch Attribution for Business Analyst

This version of the Multi-Touch Attribution demonstration is focused on the interests of the Business Analyst.
Python-SQL Version

Multi-Touch Attribution for Data Scientist

Demonstrates attribution of customer behavior via single touch and multi-touch rule-based models using statistical and algorithmic models. Multiple approaches are demonstrated.
Python-SQL Version

Predictive Maintenance

Uses ML functions to predict failures to identify and mitigate potential machine failures before they occur.
Python-SQL Version

Remaining Useful Life Forecasting

Applies machine learning to predict Remaining Useful Life (RUL) of jet engines, allowing scheduling of maintenance and replacement before failure occurs and reduces the cost of maintenance and replacement.
Python-SQL Version

Store Sales Forecast via ARIMA

Forecasts total store sales using ARIMA (AutoRegressive Integrated Moving Average)
Python Version

Store Sales Forecast via Prophet

Uses the Script Table Operator (STO) to run the H20 machine learning library as an extension to ClearScape Analytics. H20 runs in parallel inside the Vantage database without exporting data to another platform.
Python-SQL Version

Telco Customer Churn

This uses logistic regression for supervised learning to predict the probability of a customer switching vendors based on usage patterns, billing information demographics and interactions. XGBoost is then used in database to improve the prediction.
Python VersionVideo

Train Delay Path Analysis

Uses nPath displays to show relationship of delays and predictive models to anticipate potential delays and enable proactive planning.
Python Version

VAL Analytics and ML

Demonstration of Vantage Analytic Library scoring and analytic functions like linear regression, decision trees, K-Means clustering, Factor Analysis, etc.
SQL Version

Vertex AI Integration

In this tutorial, we will show how to integrate Vantage Analytics capabilities in Vertex AI ML Pipelines. Vertex AI is the environment for data scientists to deploy ML models.
Python Version

Data Quality Anomaly Detection using Statistical Techniques

Compare the distribution and variation of data between two time intervals usin In-DB function executed via a framework to provide alerts highlighting data anomalies.
Python Version

Hyperparameter Tuning using the Titanic Passenger Dataset

Create a predictive algorithm that can identify whethr or not passengers on the Titanic survived the ship's sinking.
Python Version

Anomaly Detection in Spot Welding Process - Trusted AI

Evaluates potential failures in spot welds based on voltage anomalies during the welding process.
Python Version

Cancer Prediction using the TDAPIClient and VertexAI

Use TDAPIClient to connect to the Google Cloud Vertex API Endpoint to orchestrate Extreme Gradient XG Boost model training and score the model in SageMaker. Deploy the solution's ML model.
Python Version

Credit Risk Assessment using Teradataml OpenSource Functions

Use inDb functions with OpensourceML to create multiple DecisionTreeClassifiers to create multiple predictions of a Credit Risk Assessment.
Python Version

Financial Fraud Detection InDB

Detect financial transaction fraud using powerful in-database machine learning functions
Python VersionR Version

Predicting Medical Expenses in Healthcare

Use a dataset containing variables like age, sex, BMI, smoking status, number of children, and region to build machine learning models that accurately predict healthcare costs for insurance policyholders, taking into account factors that affect medical expenses.
Python Version

Resume Classification Model Training using Vantage In-DB Functions

Use data from a collection of Resume Examples taken from kaggle for categorizing a given resume into any of the labels defined in the dataset. Summarize and ask questions using a ChatBot.
Python Version

Cancer Prediction using Teradata and the SageMaker API

Use the Vantage SageMaker API feature to connect to an Amazon Endpoint to orchestrate Extreme Gradient XG Boost model training and score the model in SageMaker. Deploy the solution's ML model.
Python Version

Parkinson's Disease Prediction using Signal Processing

Detect Parkinson's Disease at an early stage by using Vantage InDB functions for model training and scoring to compare the performance of two models against biomedical voice measurements.
Python Version

Back to Table of Contents

ModelOps

ModelOps Introduction & List of Notebooks

This introduction and table of contents introduces you to ModelOps and provides a launch for ModelOps. It is recommended to go through ModelOps demonstrations in sequence.
Information

Back to Table of Contents

Natural Language Processing

Natural Language Processing

Use NLP for Sentiment Analysis, perform Kmeans clustering, execute Principal Component Analysis (PCA) using comments received by a Retail Store
Python-SQL Version

Back to Table of Contents

Object Storage

Battery Defect Analysis

Uses local data (or foreign tables on GCP) to analyze patterns of battery failure, then links to data on AWS for detailed battery measurement.
Python Version

Deep History via Object Store

This demonstrates integration of local data or foreign tables on GCP and integration across cloud providers to detailed historical sales records on AWS.
SQL Version

Sensor Data Analytics

Creative application of geospatial to locations of sensors in a research lab and integration of data from tables with detailed recordings on cloud storage.
Python-SQL Version

Back to Table of Contents

Open Source

Parkinson's Disease Prediction using Signal Processing

Detect Parkinson's Disease at an early stage by using Vantage InDB functions for model training and scoring to compare the performance of two models against biomedical voice measurements.
Python Version

Semantic Clustering using OpenSource Language Models

Bring a language model into Vantage and run NLP models in the database
Python Version

Semantic Similarity using OpenSource Language Models

Run Hugging Face Embedding Model in ONNX format to create some embeddings from a Consumer Complaints dataset
Python Version

Back to Table of Contents

Open-and-connected analytics

Vehicle Routing for Delivery

Demonstrates advanced analytics to find lowest cost routes to deliver a large volume of packages by a fleet of vehicles.
Python-SQL Version

Anomaly Detection

Evaluates potential failures in spot welds based on voltage anomalies during the welding process.
Python-SQL VersionVideo

Banking Customer Churn

Uses a combination of Vantage Analytics Library to prepare data, using machine learning in python and importing the resulting PMML model into Vantage for scoring.
Python Version

Back to Table of Contents

Path Analytics

Broken Digital Journey

This uses nPath® analysis to show the retail events that prevent the ultimate objective: a purchase. This uses interactive Sankey diagrams to understand the problems.
Python VersionVideo

Customer Behavior Analysis

Analysis of customer purchase behavior using nPath® analysis in Python with visualization using Sankey diagrams.
Python VersionSQL Version

Back to Table of Contents

Open-and-connected analytics

Dataiku

Discusses how the 3rd party tool DataIku can be used with Vantage.
Information

Diabetes Prediction via BYOM H2O

This uses BYOM to import a trained H2O model to identify potential diabetes patients. BYOM allows the data scientist to create models in languages they prefer and run at scale inside Vantage without moving data.
Python-SQL Version

Energy Consumption Forecasting

This combines machine learning and BYOM to forecast energy consumption using Vantage to score the model at scale without having to export all data.
Python Version

Energy Consumption Forecasting Dataiku

Demonstration of using Dataiku with Vantage. Instructions provided for use with your Dataiku copy + screen shots if you don't have Dataiku. PMML model from Dataiku is imported to Vantage for execution and scoring.
Python Version

Back to Table of Contents

Path Analytics

Financial Customer Journey

Uses analytic techniques to find new customers, measure marketing attribution, and maximizing marketing effectiveness
Python-SQL VersionSQL VersionVideo

Back to Table of Contents

Open-and-connected analytics

Financial Fraud Detection VIA BYOM

A model that was developed externally is imported into Vantage for evaluation and execution at scale to detect fraud.
Python Version

Back to Table of Contents

Path Analytics

Knee Replacement Attribution

The ClearScape Analytics Attribution function is used to determine the weight of various events that precede the final outcome, in this example, knee replacement.
SQL Version

Knee Replacement nPath

This uses the ClearScape Analytics nPath® function to provide visuals on the events leading up to the final outcome, in this case, knee replacement.
Python Version

Back to Table of Contents

Open-and-connected analytics

teradataml Python Basics

Introduction to Teradataml package for Python including connecting to Vantage, Teradata DataFrames, data manipulation and export to Pandas.
Python Version

Back to Table of Contents

Path Analytics

Train Delay Path Analysis

Uses nPath displays to show relationship of delays and predictive models to anticipate potential delays and enable proactive planning.
Python Version

Back to Table of Contents

Open-and-connected analytics

Vertex AI Integration

In this tutorial, we will show how to integrate Vantage Analytics capabilities in Vertex AI ML Pipelines. Vertex AI is the environment for data scientists to deploy ML models.
Python Version

Anomaly Detection in Spot Welding Process - Trusted AI

Evaluates potential failures in spot welds based on voltage anomalies during the welding process.
Python Version

Back to Table of Contents

PCA (Principal Component Analysis)

Customer Segmentation with K-means

Use K-means clustering to segment customers by purchase volume and value using R and tdplyr
R Version

Back to Table of Contents

Polarity Classification

Sentiment Analysis with Google Gemini

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Back to Table of Contents

Prediction Analysis

Cancer Prediction using the TDAPIClient and VertexAI

Use TDAPIClient to connect to the Google Cloud Vertex API Endpoint to orchestrate Extreme Gradient XG Boost model training and score the model in SageMaker. Deploy the solution's ML model.
Python Version

Customer Segmentation with K-means

Use K-means clustering to segment customers by purchase volume and value using R and tdplyr
R Version

Cancer Prediction using Teradata and the SageMaker API

Use the Vantage SageMaker API feature to connect to an Amazon Endpoint to orchestrate Extreme Gradient XG Boost model training and score the model in SageMaker. Deploy the solution's ML model.
Python Version

Back to Table of Contents

Sentiment Analysis

Insights from Sentiment Analysis with AWS Bedrock

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Customer Complaints Analysis with Customer360 with Google Gemini

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Sentiment Analysis with Google Gemini

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Customer Complaints Analysis with Customer360 with AWS Bedrock

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Sentiment Analysis with OpenAI

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Speech Recognition and Sentiment Analysis with OpenAI

Analyzing consumer complaints using audio files conversations
Python Version

Back to Table of Contents

Signal Processing

Parkinson's Disease Prediction using Signal Processing

Detect Parkinson's Disease at an early stage by using Vantage InDB functions for model training and scoring to compare the performance of two models against biomedical voice measurements.
Python Version

Back to Table of Contents

TeradataML Open Source Functions

Predicting Medical Expenses in Healthcare

Use a dataset containing variables like age, sex, BMI, smoking status, number of children, and region to build machine learning models that accurately predict healthcare costs for insurance policyholders, taking into account factors that affect medical expenses.
Python Version

Back to Table of Contents

Text Analysis

Customer 360

This integrates data about customers from multiple sources using multiple matching techniquest to create the "Golden Customer Record" and calculate LTV.
SQL Version

Text Term Frequency

Use NGram splitter to analyze comments retail products to determine patterns of words used to describe products.
Python VersionPython-SQL VersionSQL Version

VAL Descriptive Statistics

This performs in-database analysis of data values, distribution, histograms, and text field analysis using SQL to access the Vantage Analytics Library.
SQL Version

Natural Language Processing

Use NLP for Sentiment Analysis, perform Kmeans clustering, execute Principal Component Analysis (PCA) using comments received by a Retail Store
Python-SQL Version

Back to Table of Contents

Time series analytics

Supply Chain Visibility

Shows the integration of data from warehouse, trucking company, and customer Order Management Systems (OMS) using temporal to reconcile different update frequencies and show rerouting when warehouse is unavailable.
Python Version

4D Analytics on bike sharing

Demonstration of Geospatial and TimeSeries using Austin bike trip data between 2014 and 2017.
Python-SQL VersionSQL Version

Air Passenger Forecasting

Applies Auto Regressive Integrated Moving Average (ARIMA) analysis to forecast airplane passenger volume.
SQL Version

Carbon Footprint Analytics

A key component of ESG is Carbon Footprint. This demonstrates a part of a solution available from Teradata to integrate multiple data sources to calculate carbon footprint of various corporate activities.
Python-SQL Version

Cash Demand Forecasing

Predicts the future demand for cast in Automatic Teller Machines (ATMs) using Auto Regressive Integrated Moving Average (ARIMA) using In-Database functions.
SQL Version

Consumer Complaints

Uses government consumer complaint data with SQL queries and visualizations to identify source of top complaints.
SQL Version

Energy Consumption Forecasting

This combines machine learning and BYOM to forecast energy consumption using Vantage to score the model at scale without having to export all data.
Python Version

Fourier Transforms

Fourier transformations are demonstrated to filter out noise from signals to allow identification of underlying patterns.
SQL Version

Insurance Policy Temporal

Show As-IS/As-Was capabilities of Vantage Temporal to dramatically simplify the SQL and improve performance for analyzing insurance policies versus claims.
SQL Version

NYC Taxi Temporal

Time series data can answer the questions about what was happening at a point in time. This applies Time series and temporal capabilities of vantage to NYC taxi data.
SQL Version

Retail Demand Forecasting

This creates an ARIMA time series model based on holidays and merchandising activities impacting store sales for a hypermarket retailer.
Python Version

Vantage Query Log Analysis

Analysis of sessions and queries you executed using the built-in logging facilities of Vantage.
SQL Version

Enhance Product Hierarchies with In-DB K-means Clustering

Enhance a product hierarchy by leveraging time series analysis and clustering techniques
Python Version

Back to Table of Contents

Topic Modelling

Customer Complaints Analysis with Customer360 with AWS Bedrock

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Topic Modelling with AWS Bedrock

Uncover hidden insights from vast amounts of consumer complaints data to enable the identification of trends.
Python Version

Topic Modelling with Google Gemini

Uncover hidden insights from vast amounts of consumer complaints data to enable the identification of trends.
Python Version

Customer Complaints Analysis with Customer360 with Google Gemini

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Topic Modelling with OpenAI

Uncover hidden insights from vast amounts of consumer complaints data to enable the identification of trends.
Python Version

Back to Table of Contents

Unbounded Array Framework

Signal Processing and Classification

Use the Unbounded Array Framework in ClearScape Analytics to classify sonar signals. Extract and engineer features to use in training and scoring our models.
Python Version

Back to Table of Contents


3rd Party Tools

AWS SageMaker

Cancer Prediction using Teradata and the SageMaker API

Use the Vantage SageMaker API feature to connect to an Amazon Endpoint to orchestrate Extreme Gradient XG Boost model training and score the model in SageMaker. Deploy the solution's ML model.
Python Version

Generate Teradata SQL with GenAI and AWS Bedrock

In this demo, we use AWS Bedrock's LLMs and LangChain to create a text-to-Teradata SQL agent.
Python Version

Back to Table of Contents

Azure ML

Energy Consumption Forecasting using AzureML

This leverages the power of AzureML and Teradata Vantage to enhance our machine learning capabilities and enable scalable model scoring to forecast energy consumption.
Python Version

Back to Table of Contents

Celebrus

Digital Identity Management

Combines ClearScape Analytics with Celebrus to track unique customers across web sessions and devices to drive personalized experiences
SQL Version

Back to Table of Contents

Dataiku

Dataiku

Discusses how the 3rd party tool DataIku can be used with Vantage.
Information

Energy Consumption Forecasting Dataiku

Demonstration of using Dataiku with Vantage. Instructions provided for use with your Dataiku copy + screen shots if you don't have Dataiku. PMML model from Dataiku is imported to Vantage for execution and scoring.
Python Version

Back to Table of Contents

H2O.ai

ModelOps Introduction & List of Notebooks

This introduction and table of contents introduces you to ModelOps and provides a launch for ModelOps. It is recommended to go through ModelOps demonstrations in sequence.
Information

Back to Table of Contents

SAS

Sales Forecasting with Vantage vs SAS

This demo walks through how a typical SAS user would use sales data to build a simple sales forecasting model and then will showcase how we can achieve the same using Vantage ClearScape Analytics.
Python-SQL VersionSQL Version

Back to Table of Contents

Vertex AI

Cancer Prediction using the TDAPIClient and VertexAI

Use TDAPIClient to connect to the Google Cloud Vertex API Endpoint to orchestrate Extreme Gradient XG Boost model training and score the model in SageMaker. Deploy the solution's ML model.
Python Version

Vertex AI Integration

In this tutorial, we will show how to integrate Vantage Analytics capabilities in Vertex AI ML Pipelines. Vertex AI is the environment for data scientists to deploy ML models.
Python Version

Back to Table of Contents

AWS Bedrock

Complaints Classification with AWS Bedrock

Classify customer complaints to swiftly identify and address concerns.
Python Version

Complaints Clustering with AWS Bedrock

Use advanced clustering techniques using AI Embeddings model to group similar customer complaints together.
Python Version

Complaints Summarization with AWS Bedrock

Efficiently manage and analyze customer complaints, providing actionable insights to enhance customer satisfaction and improve business operations.
Python Version

Insights from Sentiment Analysis with AWS Bedrock

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Topic Modelling with AWS Bedrock

Uncover hidden insights from vast amounts of consumer complaints data to enable the identification of trends.
Python Version

Customer Complaints Analysis with Customer360 with AWS Bedrock

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Product Recommendation via AWS Bedrock

Use AWS Bedrock, Embedding from HuggingFace and Vantage in-DB functions to assist in providing product recommendations to develop a recipe assistant chatbot.
Python Version

Speech Recognition and Sentiment Analysis with AWS Bedrock

Analyzing consumer complaints using audio files conversations
Python Version

Customer Complaint Analysis with AWS Bedrock

This is a collection of demos showing multiple methods of dealing with customer complaints using various GenAI techniques.
Information

Customer Reviews Analysis using GenAI

Customer reviews analysis is a crucial aspect of understanding customer sentiment and preferences. By leveraging the power of OpenAIEmbeddings and Vantage InDB Analytic Function, we can gain valuable insights from customer reviews.
Python Version

Generate Teradata SQL with GenAI and AWS Bedrock

In this demo, we use AWS Bedrock's LLMs and LangChain to create a text-to-Teradata SQL agent.
Python Version

RAG Solution with Vantage Model Catalog and AWS Bedrock

Explore how to do extract data from metadata tables of Teradata using embedding and vector db style indexing in Vantage and then query LLM with context/prompts to get the details
Python Version

RAG Solution with Embedding/Chunking with Vantage and AWS Bedrock

Chunk PDFs, run embedding, try vector db style indexing in Vantage and then query Language Model with context/prompts after semantic search
Python Version

Back to Table of Contents

OpenAI

Customer Complaints Analysis Dashboard with OpenAI

This is a Dashboard with descriptions and links to various notebooks on various topics using Teradata Vantage and Microsoft Azure.
Information

Using ClearScape Analytics with openAI

To ensure optimal utilization of the OpenAI API in generative AI notebooks, it is essential to establish the API keys correctly. This concise guide outlines the process of configuring OpenAI API keys for seamless integration across multiple notebooks.
Information

Getting Started with Azure OpenAI

Follow these instructions to setup the Azure OpenAI endpoint and generate the access Keys required to run the model.
Python Version

Mental Health Chat with Fine-tuned OpenAI Model

Train a GPT-3.5 Turbo model using the OpenAI API endpoint. Ask mental health questions using a chat input box.
Python Version

Mortgage Calculator Chatbot using GenAI: Finetune LLM

Fine-tuned an OpenAI model using RAG, LangChain and LLM models framework. Query a chatbot for answers about a mortgage and available housing within a predefiend area.
Python Version

Mortgage Calculator chatbot using GenAI: RAG

Build a conversational chatbot and ask questions about a mortgage and available housing within a predefined area using LangChain.
Python Version

Resume Classification Model Training using Vantage In-DB Functions

Use data from a collection of Resume Examples taken from kaggle for categorizing a given resume into any of the labels defined in the dataset. Summarize and ask questions using a ChatBot.
Python Version

Mortgage Calculator Chatbot using Trusted AI(RAG)

Experience the integration of LLM models to provide user-friendly responses to queries. RAG combines retrieval and generative approaches.
Python Version

Customer Reviews Analysis using GenAI

Customer reviews analysis is a crucial aspect of understanding customer sentiment and preferences. By leveraging the power of OpenAIEmbeddings and Vantage InDB Analytic Function, we can gain valuable insights from customer reviews.
Python Version

Complaints Classification with OpenAI

Classify customer complaints to swiftly identify and address concerns.
Python Version

Complaints Clustering with OpenAI

Use advanced clustering techniques using AI Embeddings model to group similar customer complaints together.
Python Version

Complaints Summarization with OpenAI

Efficiently manage and analyze customer complaints, providing actionable insights to enhance customer satisfaction and improve business operations.
Python Version

Customer Complaints Analysis with Customer360 with OpenAI

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Sentiment Analysis with OpenAI

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Speech Recognition and Sentiment Analysis with OpenAI

Analyzing consumer complaints using audio files conversations
Python Version

Topic Modelling with OpenAI

Uncover hidden insights from vast amounts of consumer complaints data to enable the identification of trends.
Python Version

Back to Table of Contents

Google Gemini

Customer Complaint Analysis with Google Gemini

This is a Dashboard with descriptions and links to various notebooks on various topics using Teradata Vantage and Google Gemini.
Information

Complaints Classification with Google Gemini

Classify customer complaints to swiftly identify and address concerns.
Python Version

Complaints Clustering with Google Gemini

Use advanced clustering techniques using AI Embeddings model to group similar customer complaints together.
Python Version

Complaints Summarization with Google Gemini

Efficiently manage and analyze customer complaints, providing actionable insights to enhance customer satisfaction and improve business operations.
Python Version

Customer Complaints Analysis with Customer360 with Google Gemini

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Sentiment Analysis with Google Gemini

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Speech Recognition and Sentiment Analysis with Google Gemini

Analyzing consumer complaints using audio files conversations
Python Version

Topic Modelling with Google Gemini

Uncover hidden insights from vast amounts of consumer complaints data to enable the identification of trends.
Python Version

Back to Table of Contents

Hugging Face

Initiate Parallel CPU Inferencing of Hugging Face Models in Vantage

Execute this notebook first to prepare the environment to demonstrate Parallel CPU Inferencing of Hugging Face Models in Vantage
Python Version

RAG Solution with Embedding/Chunking with Vantage and AWS Bedrock

Chunk PDFs, run embedding, try vector db style indexing in Vantage and then query Language Model with context/prompts after semantic search
Python Version

RAG Solution with Vantage Model Catalog and AWS Bedrock

Explore how to do extract data from metadata tables of Teradata using embedding and vector db style indexing in Vantage and then query LLM with context/prompts to get the details
Python Version

Semantic Clustering using OpenSource Language Models

Bring a language model into Vantage and run NLP models in the database
Python Version

Semantic Similarity using OpenSource Language Models

Run Hugging Face Embedding Model in ONNX format to create some embeddings from a Consumer Complaints dataset
Python Version

Back to Table of Contents


Language

Python

Anomaly Detection of Outstanding Amounts

Anomaly detection in bank accounts can help in identifying unusual patterns, potentially flagging issues like errors or fraudulent activities. Enterprise re-use of Features ensures rapid creation & deployment of models while new Features can be created and used without extensive engineering support.
Python Version

Charting and Visualizations using teradataml

The td_plot method streamlines large-scale visualizations by providing users with efficient tools to create visualizations directly within the Vantage platform
Python Version

Chatbot using GenAI with insurance PDF document

Uses TD_VectorDistance in Vantage to create a chatbot using Retrieval-Augmented Generation (RAG), Langchain, and LLM to answer questions using a 24 page travelers insurance policy PDF as source data to answer questions about coverage.
Python VersionPython-SQL Version

Credit Card Data Preparation

Uses functions from TeradataML Python library to prepare data for analysis using data cleansing, exploration and feature engineering functions.
Python Version

ModelOps Introduction & List of Notebooks

This introduction and table of contents introduces you to ModelOps and provides a launch for ModelOps. It is recommended to go through ModelOps demonstrations in sequence.
Information

Mortgage Calculator using GenAI

Use Retrieval-Augmented Generation (RAG), Lanchain and LLM models to as questions about loans and retrieve relevant data from Vantage.
Python Version

Product Recommentations via TDApiClient

Build a product recommendation system using OpenAI embeddings and Vantage in db_function VectorDistance. We will also use Vantage as VectorDB, to store the embeddings.
Python Version

Sales Forecasting with Vantage vs SAS

This demo walks through how a typical SAS user would use sales data to build a simple sales forecasting model and then will showcase how we can achieve the same using Vantage ClearScape Analytics.
Python-SQL VersionSQL Version

Shipping Time Prediction

Use ClearScape Analytics to develop a robust system that can reliably estimate delivery dates, accounting for handling time, transit time, and other relevant variables affecting the actual delivery timeframe.
Python-SQL Version

Supply Chain Visibility

Shows the integration of data from warehouse, trucking company, and customer Order Management Systems (OMS) using temporal to reconcile different update frequencies and show rerouting when warehouse is unavailable.
Python Version

Vehicle Routing for Delivery

Demonstrates advanced analytics to find lowest cost routes to deliver a large volume of packages by a fleet of vehicles.
Python-SQL Version

Grocery Recommendations using GenAI

Use context-based product recommendations powered by GenAI Large Language Models to enhance a shopping experience.
Python-SQL Version

Hyperparameter Tuning using the Titanic Passenger Dataset

Create a predictive algorithm that can identify whethr or not passengers on the Titanic survived the ship's sinking.
Python Version

Signal Processing and Classification

Use the Unbounded Array Framework in ClearScape Analytics to classify sonar signals. Extract and engineer features to use in training and scoring our models.
Python Version

Customer Complaint Analysis with Google Gemini

This is a Dashboard with descriptions and links to various notebooks on various topics using Teradata Vantage and Google Gemini.
Information

Getting Started with Azure OpenAI

Follow these instructions to setup the Azure OpenAI endpoint and generate the access Keys required to run the model.
Python Version

Natural Language Processing

Use NLP for Sentiment Analysis, perform Kmeans clustering, execute Principal Component Analysis (PCA) using comments received by a Retail Store
Python-SQL Version

Speech Recognition and Sentiment Analysis with AWS Bedrock

Analyzing consumer complaints using audio files conversations
Python Version

Tutorial on using Teradataml Widgets

Use Teradataml Widgets to display interactive prompting to generate datasets from the Vantage database.
Python Version

Convert PySpark to teradatamlspk

Convert a PySpark script to teradatamlspk syntax and generate a HTML report using Housing Prices to generate price predictions.
Python Version

Customer Complaints Analysis with Customer360 with AWS Bedrock

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Generate Teradata SQL with GenAI and AWS Bedrock

In this demo, we use AWS Bedrock's LLMs and LangChain to create a text-to-Teradata SQL agent.
Python Version

Introduction to Plot types using Teradataml Widgets.

This is an introduction to using the various Plot types available as widgets: Line, Bar, Mesh, Wiggle, Geometry, etc.
Python Version

Sales Forecasting using Teradata AUTOARIMA

Forecast the amount of future sales by developing a time-series modelling pipeline using Vantage and In-DB analytics
Python Version

Streamlining Analytics with Hyper-Segmented Models

By addressing unique customer behaviors and preferences within specific micro-segments, enhance customer satisfaction, boost operational efficiency, and improve profitability by to deploying and managing hyper-segmented models at scale.
Python Version

Banking Churn Prediction with AutoML

Implement the entire lifecycle of churn prediction using BYOM, VAL and AutoML.
Python Version

Complaints Classification with OpenAI

Classify customer complaints to swiftly identify and address concerns.
Python Version

Complaints Clustering with AWS Bedrock

Use advanced clustering techniques using AI Embeddings model to group similar customer complaints together.
Python Version

Complaints Clustering with OpenAI

Use advanced clustering techniques using AI Embeddings model to group similar customer complaints together.
Python Version

Complaints Summarization with OpenAI

Efficiently manage and analyze customer complaints, providing actionable insights to enhance customer satisfaction and improve business operations.
Python Version

Credit Risk Assessment using Teradataml OpenSource Functions

Use inDb functions with OpensourceML to create multiple DecisionTreeClassifiers to create multiple predictions of a Credit Risk Assessment.
Python Version

Customer Complaints Analysis with Customer360 with OpenAI

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Customer Reviews Analysis using GenAI

Customer reviews analysis is a crucial aspect of understanding customer sentiment and preferences. By leveraging the power of OpenAIEmbeddings and Vantage InDB Analytic Function, we can gain valuable insights from customer reviews.
Python Version

Data Quality Anomaly Detection using Statistical Techniques

Compare the distribution and variation of data between two time intervals usin In-DB function executed via a framework to provide alerts highlighting data anomalies.
Python Version

Execute Custom Python Scripts in Vantage

Run an external custom python script in Vantage using Script Table Operator(STO) to execute custom python scripts on Vantage
Python Version

Mental Health Chat with Fine-tuned OpenAI Model

Train a GPT-3.5 Turbo model using the OpenAI API endpoint. Ask mental health questions using a chat input box.
Python Version

Mortgage Calculator chatbot using GenAI: RAG

Build a conversational chatbot and ask questions about a mortgage and available housing within a predefined area using LangChain.
Python Version

Mortgage Calculator Chatbot using Trusted AI(RAG)

Experience the integration of LLM models to provide user-friendly responses to queries. RAG combines retrieval and generative approaches.
Python Version

Parkinson's Disease Prediction using Signal Processing

Detect Parkinson's Disease at an early stage by using Vantage InDB functions for model training and scoring to compare the performance of two models against biomedical voice measurements.
Python Version

Sentiment Analysis with OpenAI

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Speech Recognition and Sentiment Analysis with OpenAI

Analyzing consumer complaints using audio files conversations
Python Version

Topic Modelling with OpenAI

Uncover hidden insights from vast amounts of consumer complaints data to enable the identification of trends.
Python Version

Anomaly Detection in Spot Welding Process - Trusted AI

Evaluates potential failures in spot welds based on voltage anomalies during the welding process.
Python Version

Cancer Prediction using the TDAPIClient and VertexAI

Use TDAPIClient to connect to the Google Cloud Vertex API Endpoint to orchestrate Extreme Gradient XG Boost model training and score the model in SageMaker. Deploy the solution's ML model.
Python Version

Customer Complaints Analysis Dashboard with OpenAI

This is a Dashboard with descriptions and links to various notebooks on various topics using Teradata Vantage and Microsoft Azure.
Information

Product Recommendation via AWS Bedrock

Use AWS Bedrock, Embedding from HuggingFace and Vantage in-DB functions to assist in providing product recommendations to develop a recipe assistant chatbot.
Python Version

Resume Classification Model Training using Vantage In-DB Functions

Use data from a collection of Resume Examples taken from kaggle for categorizing a given resume into any of the labels defined in the dataset. Summarize and ask questions using a ChatBot.
Python Version

Customer Complaint Analysis with AWS Bedrock

This is a collection of demos showing multiple methods of dealing with customer complaints using various GenAI techniques.
Information

Financial Fraud Detection InDB

Detect financial transaction fraud using powerful in-database machine learning functions
Python VersionR Version

Initiate Parallel CPU Inferencing of Hugging Face Models in Vantage

Execute this notebook first to prepare the environment to demonstrate Parallel CPU Inferencing of Hugging Face Models in Vantage
Python Version

Predicting Medical Expenses in Healthcare

Use a dataset containing variables like age, sex, BMI, smoking status, number of children, and region to build machine learning models that accurately predict healthcare costs for insurance policyholders, taking into account factors that affect medical expenses.
Python Version

RAG Solution with Embedding/Chunking with Vantage and AWS Bedrock

Chunk PDFs, run embedding, try vector db style indexing in Vantage and then query Language Model with context/prompts after semantic search
Python Version

RAG Solution with Vantage Model Catalog and AWS Bedrock

Explore how to do extract data from metadata tables of Teradata using embedding and vector db style indexing in Vantage and then query LLM with context/prompts to get the details
Python Version

Semantic Clustering using OpenSource Language Models

Bring a language model into Vantage and run NLP models in the database
Python Version

Semantic Similarity using OpenSource Language Models

Run Hugging Face Embedding Model in ONNX format to create some embeddings from a Consumer Complaints dataset
Python Version

Complaints Classification with AWS Bedrock

Classify customer complaints to swiftly identify and address concerns.
Python Version

Complaints Classification with Google Gemini

Classify customer complaints to swiftly identify and address concerns.
Python Version

Complaints Clustering with Google Gemini

Use advanced clustering techniques using AI Embeddings model to group similar customer complaints together.
Python Version

Complaints Summarization with Google Gemini

Efficiently manage and analyze customer complaints, providing actionable insights to enhance customer satisfaction and improve business operations.
Python Version

Sentiment Analysis with Google Gemini

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Speech Recognition and Sentiment Analysis with Google Gemini

Analyzing consumer complaints using audio files conversations
Python Version

Topic Modelling with AWS Bedrock

Uncover hidden insights from vast amounts of consumer complaints data to enable the identification of trends.
Python Version

Topic Modelling with Google Gemini

Uncover hidden insights from vast amounts of consumer complaints data to enable the identification of trends.
Python Version

Insights from Sentiment Analysis with AWS Bedrock

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Customer Complaints Analysis with Customer360 with Google Gemini

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

4D Analytics on bike sharing

Demonstration of Geospatial and TimeSeries using Austin bike trip data between 2014 and 2017.
Python-SQL VersionSQL Version

Anomaly Detection

Evaluates potential failures in spot welds based on voltage anomalies during the welding process.
Python-SQL VersionVideo

Banking Customer Churn

Uses a combination of Vantage Analytics Library to prepare data, using machine learning in python and importing the resulting PMML model into Vantage for scoring.
Python Version

Battery Defect Analysis

Uses local data (or foreign tables on GCP) to analyze patterns of battery failure, then links to data on AWS for detailed battery measurement.
Python Version

Broken Digital Journey

This uses nPath® analysis to show the retail events that prevent the ultimate objective: a purchase. This uses interactive Sankey diagrams to understand the problems.
Python VersionVideo

Car Complaints

Uses geospatial techniques to locate service centers close to the complaint and outlier detection to detect part defects earlier than expected.
Python-SQL Version

Carbon Footprint Analytics

A key component of ESG is Carbon Footprint. This demonstrates a part of a solution available from Teradata to integrate multiple data sources to calculate carbon footprint of various corporate activities.
Python-SQL Version

Competitor Proximity Geospatial Analysis

This looks at the impact on purchasing when people that shop at our stores live within reasonable drive time to a competitor. This could identify proximity based marketing tactics to target larger promotions to those customers to increase share of their spend.
Python Version

Customer Behavior Analysis

Analysis of customer purchase behavior using nPath® analysis in Python with visualization using Sankey diagrams.
Python VersionSQL Version

Data Dictionary

This provides an index to all of the databases used by demo notebooks on this machine, allowing you to use that data for your own notebooks or BI tools.
Python Version

Data Dictionary Raw

This provides linkage to a larger set of databases and tables than are currently used by the demos in Jupyter.
Python Version

Data Loading (Python)

Shows how to use python to load CSV data from local storage and from zipped files
Python Version

Data Prep and Transformation

This demonstrates a subset of the over 100 analytic functions in the teradataml package for Python
Python VersionPython-SQL Version

Data Science 101 with Python

This walks through the Cross-Industry Standard Process for Data Mining (CRISP-DM) from data understanding through modeling and evaluation.
Python Version

Diabetes Prediction via BYOM H2O

This uses BYOM to import a trained H2O model to identify potential diabetes patients. BYOM allows the data scientist to create models in languages they prefer and run at scale inside Vantage without moving data.
Python-SQL Version

Diabetes Prediction via DF and GLM

Decision Forest and Generalized Linear Model are applied to identify factors that indicate diabetes. The earlier the disease is identified, the better the chance of reducing organ damage.
Python Version

Energy Consumption Forecasting

This combines machine learning and BYOM to forecast energy consumption using Vantage to score the model at scale without having to export all data.
Python Version

Energy Consumption Forecasting Dataiku

Demonstration of using Dataiku with Vantage. Instructions provided for use with your Dataiku copy + screen shots if you don't have Dataiku. PMML model from Dataiku is imported to Vantage for execution and scoring.
Python Version

Energy Consumption Forecasting using AzureML

This leverages the power of AzureML and Teradata Vantage to enhance our machine learning capabilities and enable scalable model scoring to forecast energy consumption.
Python Version

Financial Customer Journey

Uses analytic techniques to find new customers, measure marketing attribution, and maximizing marketing effectiveness
Python-SQL VersionSQL VersionVideo

Financial Fraud Detection InDB

Detect financial transaction fraud using powerful in-database machine learning functions
Python VersionVideo

Financial Fraud Detection VIA BYOM

A model that was developed externally is imported into Vantage for evaluation and execution at scale to detect fraud.
Python Version

Flood Proximity to Climate Risk Analysis

This allows enterprises to rapidly analyze this geographic-related information in real-time at any scale - effectively understanding the impacts of these climate events on entire populations.
Python Version

Generative AI Question Answering

Uses OpenAI to translate english language questions into SQL queries to run against a table of marketing data. This includes a link to a notebook with instructions for getting the required OpenAI API key.
Python VersionVideo

Graph Analysis of CDR Records

Uses graph analysis to identify communities and key influencers within Call Data Records. This uses Script Table Operator to invoke external procedures to work inside the Vantage database without exporting data.
Python-SQL Version

Green Manufacturing

Uses analytic and ML techniques to predict how long vehicle testing will take based on combination of features installed.
Python Version

Heart Failure Prediction

Machine learning is applied to the complex attributes of patients to help recognize patterns that may lead to heart failure faster than a human may recognize.
Python-SQL Version

How to Submit Your Demos

It is very easy to submit your demo for publication. Tell us directory with the notebook and referenced files and grant us access to your database. We'll take it from there.
Python VersionVideo

Hyper-Personalization

Hyper-personalization creates models from customer iteractions on multiple channels to determine the "Next Best Offer" for the individual.
Python-SQL Version

Intro to Panda for Python

Provides step-by-step instructions on the basics of using Python Pandas with Jupyter notebooks.
Python Version

Knee Replacement nPath

This uses the ClearScape Analytics nPath® function to provide visuals on the events leading up to the final outcome, in this case, knee replacement.
Python Version

Marketing Campaign Effectiveness

Examines the results of campaigns by various customer attributes then uses correlation, outlier elimination, and machine learning to identify the best campaigns.
Python-SQL Version

Multi-Touch Attribution for Business Analyst

This version of the Multi-Touch Attribution demonstration is focused on the interests of the Business Analyst.
Python-SQL Version

Multi-Touch Attribution for Data Scientist

Demonstrates attribution of customer behavior via single touch and multi-touch rule-based models using statistical and algorithmic models. Multiple approaches are demonstrated.
Python-SQL Version

NYC Taxi Geospatial

Applies geospatial functions to analysis of NYC Taxi pickups and drop off locations.
Python-SQL Version

Predictive Maintenance

Uses ML functions to predict failures to identify and mitigate potential machine failures before they occur.
Python-SQL Version

Product Recommendations via Open Source

Uses FlagEmbedding from HuggingFace plus Vantage in-database functions to assess the vector distance between the product entered and similar products.
Python Version

Product Recommendations via OpenAI

Uses OpenAIEmbeddings and Vantage in-database function to assists consumers in receiving product recommendations
Python Version

Query Service REST API

Demonstration of using REST API calls to Vantage which is useful for web or mobile applications to access and maintain data.
Python Version

Remaining Useful Life Forecasting

Applies machine learning to predict Remaining Useful Life (RUL) of jet engines, allowing scheduling of maintenance and replacement before failure occurs and reduces the cost of maintenance and replacement.
Python-SQL Version

Retail Demand Forecasting

This creates an ARIMA time series model based on holidays and merchandising activities impacting store sales for a hypermarket retailer.
Python Version

Sales Forecasting using UAF

A detailed coverage of the analytic steps in sales forecasting including data preparation, exploration, seasonal normalizing, model creation, validation, and forecasting.
Python Version

Sensor Data Analytics

Creative application of geospatial to locations of sensors in a research lab and integration of data from tables with detailed recordings on cloud storage.
Python-SQL Version

Store Sales Forecast via ARIMA

Forecasts total store sales using ARIMA (AutoRegressive Integrated Moving Average)
Python Version

Store Sales Forecast via Prophet

Uses the Script Table Operator (STO) to run the H20 machine learning library as an extension to ClearScape Analytics. H20 runs in parallel inside the Vantage database without exporting data to another platform.
Python-SQL Version

Telco Customer Churn

This uses logistic regression for supervised learning to predict the probability of a customer switching vendors based on usage patterns, billing information demographics and interactions. XGBoost is then used in database to improve the prediction.
Python VersionVideo

Telco Network Coverage

Demonstrates the ability of Geospatial to show signal strength, coverage areas and travel path of customers through cell tower coverage area.
Python Version

teradataml Python Basics

Introduction to Teradataml package for Python including connecting to Vantage, Teradata DataFrames, data manipulation and export to Pandas.
Python Version

Text Term Frequency

Use NGram splitter to analyze comments retail products to determine patterns of words used to describe products.
Python VersionPython-SQL VersionSQL Version

Train Delay Path Analysis

Uses nPath displays to show relationship of delays and predictive models to anticipate potential delays and enable proactive planning.
Python Version

VAL teradataml Demo

Demonstrated the use of Teradataml in Python to perform descriptive statistics, transformation, model building model evaluation and scoring.
Python Version

Vertex AI Integration

In this tutorial, we will show how to integrate Vantage Analytics capabilities in Vertex AI ML Pipelines. Vertex AI is the environment for data scientists to deploy ML models.
Python Version

Back to Table of Contents

SQL

Chatbot using GenAI with insurance PDF document

Uses TD_VectorDistance in Vantage to create a chatbot using Retrieval-Augmented Generation (RAG), Langchain, and LLM to answer questions using a 24 page travelers insurance policy PDF as source data to answer questions about coverage.
Python VersionPython-SQL Version

Sales Forecasting with Vantage vs SAS

This demo walks through how a typical SAS user would use sales data to build a simple sales forecasting model and then will showcase how we can achieve the same using Vantage ClearScape Analytics.
Python-SQL VersionSQL Version

Shipping Time Prediction

Use ClearScape Analytics to develop a robust system that can reliably estimate delivery dates, accounting for handling time, transit time, and other relevant variables affecting the actual delivery timeframe.
Python-SQL Version

Telco 5G Quality of Experience

Quality of service analysis of 5G vs 4G video for different situations such as Indoor, outdoor, and moble.
SQL Version

Customer Behavior Analysis

Analysis of customer purchase behavior using nPath® analysis in Python with visualization using Sankey diagrams.
Python VersionSQL Version

Grocery Recommendations using GenAI

Use context-based product recommendations powered by GenAI Large Language Models to enhance a shopping experience.
Python-SQL Version

4D Analytics on bike sharing

Demonstration of Geospatial and TimeSeries using Austin bike trip data between 2014 and 2017.
Python-SQL VersionSQL Version

Air Passenger Forecasting

Applies Auto Regressive Integrated Moving Average (ARIMA) analysis to forecast airplane passenger volume.
SQL Version

Basic Jupyter Navigation

When running a Jupyter Notebook, there are various indicators that show what is happening. This is a guide to those indicators.
SQL Version

Cash Demand Forecasing

Predicts the future demand for cast in Automatic Teller Machines (ATMs) using Auto Regressive Integrated Moving Average (ARIMA) using In-Database functions.
SQL Version

Charting and Visualization

Data from queries is brought to life with graphics and charts. This shows how to use the %chart magic command to display results.
SQL Version

Consumer Complaints

Uses government consumer complaint data with SQL queries and visualizations to identify source of top complaints.
SQL Version

Credit Card Data Preparation

This shows the use of ClearScape analytics to reduce the pre-processing effort of incoming raw credit card data to prepare for analysis of potential loan defaulters.
SQL Version

Customer 360

This integrates data about customers from multiple sources using multiple matching techniquest to create the "Golden Customer Record" and calculate LTV.
SQL Version

Data Loading (SQL)

Shows multiple ways to load data from local CSV files, and cloud files on Google and AWS using the SQL kernel.
SQL Version

Deep History via Object Store

This demonstrates integration of local data or foreign tables on GCP and integration across cloud providers to detailed historical sales records on AWS.
SQL Version

Digital Identity Management

Combines ClearScape Analytics with Celebrus to track unique customers across web sessions and devices to drive personalized experiences
SQL Version

Financial Customer Journey

Uses analytic techniques to find new customers, measure marketing attribution, and maximizing marketing effectiveness
Python-SQL VersionSQL VersionVideo

Fourier Transforms

Fourier transformations are demonstrated to filter out noise from signals to allow identification of underlying patterns.
SQL Version

Insurance Policy Temporal

Show As-IS/As-Was capabilities of Vantage Temporal to dramatically simplify the SQL and improve performance for analyzing insurance policies versus claims.
SQL Version

K-Means Clustering and ML model

This uses the unsupervised K-Means ML algorithm to identify patterns in retail purchases.
SQL Version

Knee Replacement Attribution

The ClearScape Analytics Attribution function is used to determine the weight of various events that precede the final outcome, in this example, knee replacement.
SQL Version

NYC Taxi Temporal

Time series data can answer the questions about what was happening at a point in time. This applies Time series and temporal capabilities of vantage to NYC taxi data.
SQL Version

Outlier Analysis

Outliers in an analysis skew the results and make it difficult to recognize the main patterns. ClearScape Analytics has tools to remove outliers automatically.
SQL Version

SQL Basics in Jupyter

This guide will walk you through writing your first SQL queries in Jupyter. It uses some of the Vantage system tables as a source for the queries.
SQL Version

Text Term Frequency

Use NGram splitter to analyze comments retail products to determine patterns of words used to describe products.
Python VersionPython-SQL VersionSQL Version

VAL Analytics and ML

Demonstration of Vantage Analytic Library scoring and analytic functions like linear regression, decision trees, K-Means clustering, Factor Analysis, etc.
SQL Version

VAL Descriptive Statistics

This performs in-database analysis of data values, distribution, histograms, and text field analysis using SQL to access the Vantage Analytics Library.
SQL Version

VAL Hypothesis Tests

This demonstrates a subset of the 18 hypothesis test in the Vantage Analytics library using SQL such as Parametric, Binomial, Kolmogorov/Smirnoff, Rank, etc.
SQL Version

VAL Overview

Vantage Analytics Library (VAL) is a set of over 50 functions for advanced analytics. This provides an overview and links to an 8 minute video overview.
SQL Version

Vantage Query Log Analysis

Analysis of sessions and queries you executed using the built-in logging facilities of Vantage.
SQL Version

Back to Table of Contents

R

ModelOps Introduction & List of Notebooks

This introduction and table of contents introduces you to ModelOps and provides a launch for ModelOps. It is recommended to go through ModelOps demonstrations in sequence.
Information

Customer Segmentation with K-means

Use K-means clustering to segment customers by purchase volume and value using R and tdplyr
R Version

Teradata Package for R Basics

Discoverer how the Teradata Package for R (tdplyr) allows users to develop and run R programs to take advantage of Big Data and Machine Learning analytic capabilities of Vantage.
Information

Financial Fraud Detection InDB

Detect financial transaction fraud using powerful in-database machine learning functions
Python VersionR Version

tdplyr R Basics

Work through using the bgasics of the Teradata R package, tdplyr
R Version

Data Loading ('R')

Shows multiple ways to load data from local CSV files, and cloud files on Google and AWS using the SQL kernel.
R Version

Back to Table of Contents


Solution Accelerator

Anomaly Detection

Anomaly Detection of Outstanding Amounts

Anomaly detection in bank accounts can help in identifying unusual patterns, potentially flagging issues like errors or fraudulent activities. Enterprise re-use of Features ensures rapid creation & deployment of models while new Features can be created and used without extensive engineering support.
Python Version

Anomaly Detection

Evaluates potential failures in spot welds based on voltage anomalies during the welding process.
Python-SQL VersionVideo

Data Quality Anomaly Detection using Statistical Techniques

Compare the distribution and variation of data between two time intervals usin In-DB function executed via a framework to provide alerts highlighting data anomalies.
Python Version

Back to Table of Contents

Customer Complaint Analysis

Customer Complaint Analysis with AWS Bedrock

This is a collection of demos showing multiple methods of dealing with customer complaints using various GenAI techniques.
Information

Customer Complaints Analysis with Customer360 with AWS Bedrock

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Customer Complaints Analysis Dashboard with OpenAI

This is a Dashboard with descriptions and links to various notebooks on various topics using Teradata Vantage and Microsoft Azure.
Information

Complaints Classification with AWS Bedrock

Classify customer complaints to swiftly identify and address concerns.
Python Version

Customer Complaint Analysis with Google Gemini

This is a Dashboard with descriptions and links to various notebooks on various topics using Teradata Vantage and Google Gemini.
Information

Topic Modelling with AWS Bedrock

Uncover hidden insights from vast amounts of consumer complaints data to enable the identification of trends.
Python Version

Complaints Classification with Google Gemini

Classify customer complaints to swiftly identify and address concerns.
Python Version

Complaints Clustering with Google Gemini

Use advanced clustering techniques using AI Embeddings model to group similar customer complaints together.
Python Version

Complaints Summarization with AWS Bedrock

Efficiently manage and analyze customer complaints, providing actionable insights to enhance customer satisfaction and improve business operations.
Python Version

Complaints Summarization with Google Gemini

Efficiently manage and analyze customer complaints, providing actionable insights to enhance customer satisfaction and improve business operations.
Python Version

Customer Complaints Analysis with Customer360 with Google Gemini

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Sentiment Analysis with Google Gemini

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Speech Recognition and Sentiment Analysis with AWS Bedrock

Analyzing consumer complaints using audio files conversations
Python Version

Speech Recognition and Sentiment Analysis with Google Gemini

Analyzing consumer complaints using audio files conversations
Python Version

Topic Modelling with Google Gemini

Uncover hidden insights from vast amounts of consumer complaints data to enable the identification of trends.
Python Version

Complaints Classification with OpenAI

Classify customer complaints to swiftly identify and address concerns.
Python Version

Complaints Clustering with AWS Bedrock

Use advanced clustering techniques using AI Embeddings model to group similar customer complaints together.
Python Version

Complaints Clustering with OpenAI

Use advanced clustering techniques using AI Embeddings model to group similar customer complaints together.
Python Version

Complaints Summarization with OpenAI

Efficiently manage and analyze customer complaints, providing actionable insights to enhance customer satisfaction and improve business operations.
Python Version

Customer Complaints Analysis with Customer360 with OpenAI

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Insights from Sentiment Analysis with AWS Bedrock

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Sentiment Analysis with OpenAI

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Speech Recognition and Sentiment Analysis with OpenAI

Analyzing consumer complaints using audio files conversations
Python Version

Topic Modelling with OpenAI

Uncover hidden insights from vast amounts of consumer complaints data to enable the identification of trends.
Python Version

Back to Table of Contents

Enterprise Feature Store

Anomaly Detection of Outstanding Amounts

Anomaly detection in bank accounts can help in identifying unusual patterns, potentially flagging issues like errors or fraudulent activities. Enterprise re-use of Features ensures rapid creation & deployment of models while new Features can be created and used without extensive engineering support.
Python Version

Back to Table of Contents


Other

New

Enhance Product Hierarchies with In-DB K-means Clustering

Enhance a product hierarchy by leveraging time series analysis and clustering techniques
Python Version

Execute Custom Python Scripts in Vantage

Run an external custom python script in Vantage using Script Table Operator(STO) to execute custom python scripts on Vantage
Python Version

Resume Classification Model Training using Vantage In-DB Functions

Use data from a collection of Resume Examples taken from kaggle for categorizing a given resume into any of the labels defined in the dataset. Summarize and ask questions using a ChatBot.
Python Version

Sales Forecasting using Teradata AUTOARIMA

Forecast the amount of future sales by developing a time-series modelling pipeline using Vantage and In-DB analytics
Python Version

Streamlining Analytics with Hyper-Segmented Models

By addressing unique customer behaviors and preferences within specific micro-segments, enhance customer satisfaction, boost operational efficiency, and improve profitability by to deploying and managing hyper-segmented models at scale.
Python Version

Back to Table of Contents

Parallel CPU Inferencing

RAG Solution with Embedding/Chunking with Vantage and AWS Bedrock

Chunk PDFs, run embedding, try vector db style indexing in Vantage and then query Language Model with context/prompts after semantic search
Python Version

RAG Solution with Vantage Model Catalog and AWS Bedrock

Explore how to do extract data from metadata tables of Teradata using embedding and vector db style indexing in Vantage and then query LLM with context/prompts to get the details
Python Version

Semantic Clustering using OpenSource Language Models

Bring a language model into Vantage and run NLP models in the database
Python Version

Semantic Similarity using OpenSource Language Models

Run Hugging Face Embedding Model in ONNX format to create some embeddings from a Consumer Complaints dataset
Python Version

Initiate Parallel CPU Inferencing of Hugging Face Models in Vantage

Execute this notebook first to prepare the environment to demonstrate Parallel CPU Inferencing of Hugging Face Models in Vantage
Python Version

Back to Table of Contents

Dashboard Notebook

Resume Classification Model Training using Vantage In-DB Functions

Use data from a collection of Resume Examples taken from kaggle for categorizing a given resume into any of the labels defined in the dataset. Summarize and ask questions using a ChatBot.
Python Version

Customer Complaint Analysis with Google Gemini

This is a Dashboard with descriptions and links to various notebooks on various topics using Teradata Vantage and Google Gemini.
Information

Customer Complaint Analysis with AWS Bedrock

This is a collection of demos showing multiple methods of dealing with customer complaints using various GenAI techniques.
Information

Customer Complaints Analysis Dashboard with OpenAI

This is a Dashboard with descriptions and links to various notebooks on various topics using Teradata Vantage and Microsoft Azure.
Information

Back to Table of Contents


Cloud Provider

AWS

Insights from Sentiment Analysis with AWS Bedrock

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Complaints Classification with AWS Bedrock

Classify customer complaints to swiftly identify and address concerns.
Python Version

Complaints Clustering with AWS Bedrock

Use advanced clustering techniques using AI Embeddings model to group similar customer complaints together.
Python Version

Complaints Summarization with AWS Bedrock

Efficiently manage and analyze customer complaints, providing actionable insights to enhance customer satisfaction and improve business operations.
Python Version

Topic Modelling with AWS Bedrock

Uncover hidden insights from vast amounts of consumer complaints data to enable the identification of trends.
Python Version

Customer Complaints Analysis with Customer360 with AWS Bedrock

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Speech Recognition and Sentiment Analysis with AWS Bedrock

Analyzing consumer complaints using audio files conversations
Python Version

RAG Solution with Embedding/Chunking with Vantage and AWS Bedrock

Chunk PDFs, run embedding, try vector db style indexing in Vantage and then query Language Model with context/prompts after semantic search
Python Version

RAG Solution with Vantage Model Catalog and AWS Bedrock

Explore how to do extract data from metadata tables of Teradata using embedding and vector db style indexing in Vantage and then query LLM with context/prompts to get the details
Python Version

Customer Complaint Analysis with AWS Bedrock

This is a collection of demos showing multiple methods of dealing with customer complaints using various GenAI techniques.
Information

Back to Table of Contents

Google

Complaints Classification with Google Gemini

Classify customer complaints to swiftly identify and address concerns.
Python Version

Complaints Clustering with Google Gemini

Use advanced clustering techniques using AI Embeddings model to group similar customer complaints together.
Python Version

Complaints Summarization with Google Gemini

Efficiently manage and analyze customer complaints, providing actionable insights to enhance customer satisfaction and improve business operations.
Python Version

Customer Complaints Analysis with Customer360 with Google Gemini

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Sentiment Analysis with Google Gemini

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Speech Recognition and Sentiment Analysis with Google Gemini

Analyzing consumer complaints using audio files conversations
Python Version

Topic Modelling with Google Gemini

Uncover hidden insights from vast amounts of consumer complaints data to enable the identification of trends.
Python Version

Customer Complaint Analysis with Google Gemini

This is a Dashboard with descriptions and links to various notebooks on various topics using Teradata Vantage and Google Gemini.
Information

Back to Table of Contents

Azure

Customer Complaints Analysis Dashboard with OpenAI

This is a Dashboard with descriptions and links to various notebooks on various topics using Teradata Vantage and Microsoft Azure.
Information

Getting Started With Azure

Follow these steps to create your first Azure account and create an Azure Machine Learning workspace to complete our AzureML use cases.
Information

Getting Started with Azure OpenAI

Follow these instructions to setup the Azure OpenAI endpoint and generate the access Keys required to run the model.
Python Version

Complaints Classification with OpenAI

Classify customer complaints to swiftly identify and address concerns.
Python Version

Complaints Clustering with OpenAI

Use advanced clustering techniques using AI Embeddings model to group similar customer complaints together.
Python Version

Complaints Summarization with OpenAI

Efficiently manage and analyze customer complaints, providing actionable insights to enhance customer satisfaction and improve business operations.
Python Version

Customer Complaints Analysis with Customer360 with OpenAI

Customer360 which is a comprehensive approach to managing customer complaints and feedback within the framework of a Customer 360-degree view
Python Version

Sentiment Analysis with OpenAI

Extract insights from unstructured data to identify and address customer concerns.
Python Version

Speech Recognition and Sentiment Analysis with OpenAI

Analyzing consumer complaints using audio files conversations
Python Version

Topic Modelling with OpenAI

Uncover hidden insights from vast amounts of consumer complaints data to enable the identification of trends.
Python Version

Back to Table of Contents


©2023,2024 Teradata. All Rights Reserved