Modal LLM LLama.cpp based model deployment as part of series of Model as a Service (MaaS)

Diabetic Retinopathy (DR) is a diabetes complication that affects the eyes. It is caused by damage to the blood vessels of the light-sensitive tissue at the back of the eye (retina). DR can lead to blindness if not detected and treated early.

Aditi @ Building Production Grade LLMs - * Thank you AI community for visiting my repository - Stay tuned for awesome Dev-ops AI Learning Resources ** ** If you find the repository useful please give it a star - Thank you for visiting my repository - Happy Learning **

A data science project focused on analyzing customer reviews from Amazon's fine food products. It involves data cleaning, exploratory data analysis (EDA), sentiment analysis, and machine learning models to predict review sentiments. Built using Python, Pandas, NLP techniques, and visualization tools like Matplotlib and Seaborn.

This repository demonstrates how to build a robust fraud detection system that combines supervised learning techniques with anomaly detection models. It provides end-to-end implementation, from data preprocessing and model training to deploying a real-time fraud detection API using FastAPI.

This project involves the development of a complete ML pipeline with tracking and deployment capabilities.

A machine learning project to predict customer churn for a bank using XGBoost and Random Forest models. The project includes data preprocessing, feature engineering, model training with hyperparameter tuning, and deployment using Streamlit for real-time predictions.

Streamlit Churn Predictor: A concise and impactful repository housing a Streamlit-based churn prediction application. Utilizes logistic regression to analyze customer data, offering businesses a powerful tool for identifying and addressing potential customer churn.

Designed an end-to-end ML model pipeline, forecasting department-wide sales by accounting for holiday markdown effects, spanning data collection to inferencing.

UP-Votes predictions

The project explores multiple machine learning algorithms and evaluates their performance using various metrics, such as accuracy and confusion matrices. The models tested include Logistic Regression, K-Nearest Neighbors (KNN), Naive Bayes, and Support Vector Machine (SVM). In addition, regularization techniques (L1, L2) are used to avoid overfit.

Classification of traffic signals using gradio interface.

A comprehensive case study on implementing predictive modeling in insurance

The objective of this project is to develop a machine learning model and deploy it as a user-friendly web application that predicts the resale prices of flats in Singapore.

Built a real-world email spam classifier using Support Vector Machine(SVM), achieving 98% accuracy through robust text preprocessing, TF-IDF feature extraction, and EDA. Deployed the model with Flask, enabling real-time predictions and visualization of words influencing classification.

This repository will contain the code and supplementary materials for my Streamlit sentiment detector Computer Vision model

Churn_prediction

Internship in Codeway Solution Company