Hello! My name is Mrityunjay Pathak.

I'm a data scientist who enjoys building real-world, end-to-end systems.

I love creating projects that don't just stay in notebooks, but are deployed online where people can actually use them.

Some projects I've worked on :

• AutoIQ : Car Price Prediction
  • Built a car price prediction system with FastAPI and Docker, trained on 2,800+ scraped car listings from Cars24.
  • Deployed an interactive HTML/CSS/JS application on GitHub Pages that fetches real-time predictions via the API.
• Dashly : Live Sales Dashboard
  • Designed a live Power BI dashboard connected to a Neon PostgreSQL database, containing 50,000+ sales records.
  • Automated an ETL pipeline with GitHub Actions to keep the dashboard continuously updated with real-time insights.
• Pickify : Movie Recommender System
  • Developed a content-based movie recommender system using metadata from 5,000+ movies.
  • Integrated the TMDB API to fetch and display movie posters dynamically, for a personalized user experience.

Tools and Technologies I've worked with :

• Programming Language : Python, SQL
• Libraries : NumPy, Pandas, Matplotlib, Seaborn, Plotly
• Machine Learning : Scikit-learn
• Database : MySQL
• BI Tool : Power BI, Excel
• Web Framework : FastAPI
• Containerization : Docker
• Version Control : Git
• Automation : GitHub Actions
• Shell Scripting : Bash

I'm currently seeking opportunities as a Data Scientist or a Machine Learning Engineer, where I can contribute to building data-driven solutions that create measurable business impact.

If you're looking for someone who's eager to learn, collaborate and deliver results, I'd love to connect and explore how I can add value to your team.

Kaggle  ✦  LinkedIn  ✦  GitHub  ✦  Medium  ✦  Portfolio

➔ Problem

• In the used car market, buyers and sellers often struggle to determine a fair price for their vehicles.
• This project aims to provide an accurate and transparent pricing for used cars by analyzing real-world data.

➔ Solution

• Built and deployed an end-to-end machine learning pipeline to predict used car prices from real-world data.
• Collected and cleaned 2,800+ used car records from Cars24 using Selenium and BeautifulSoup.
• Optimized memory consumption of the dataset by downcasting data types and converting to Parquet format.
• Trained models with Scikit-learn Pipelines & ColumnTransformer to avoid data leakage.
• Deployed the machine learning model as an API using FastAPI on Render.
• Built a HTML/CSS/JS application hosted on GitHub Pages to interact with the API and display predictions in real-time.
• Containerized the entire application using Docker and pushed to Docker Hub for reproducibility.

➔ Results

• Reduced dataset memory usage by 90% using optimized storage techniques.
• Achieved a 30% lower MAE and a 12% higher R2-score compared to the baseline model.
• Improved model stability by 70%, ensuring more stable and reliable predictions.

➔ Impact

• Helps car owners quickly find the right selling price for their vehicles based on real-world data.
• Makes it easier for buyers to know if a car is fairly priced before making a purchase.

➔ Problem

• Quick Buy is a leading superstore operating across the United States.
• It manages thousands of product transactions daily across multiple regions.
• The store's operations relied on manual spreadsheets and SQL queries to track business performance.
• As a result, decision-making was slowed down and made it harder to identify growth opportunities.

➔ Solution

• Designed a fully automated ETL pipeline using Python, SQLAlchemy and GitHub Actions for seamless daily data updates.
• Built custom Python ETL scripts to extract, transform and load over 50,000+ sales records into a Neon PostgreSQL database.
• Automated daily data generation (~100 new transactions daily) to simulate real-time sales activity.
• Integrated Power BI directly with the database, enabling real-time auto-refreshing dashboard without manual uploads.

➔ Key Insights

• Standard Class drives ~60% of sales (~₹5.1M) and profit (~₹897K), making it the most profitable and preferred shipping mode.
• Consumer Segment generates ~50% of revenue (~₹4.26M) and profit (~₹757K), highlighting it as the primary customer base.
• Q4 (Oct–Dec) delivers ~27% of yearly revenue, highlighting strong seasonal demand, ideal for marketing and promotions.
• Paper, Binders and Phones emerge as top-performing sub-categories, together making up ~45% of total revenue.
• West and East regions lead the market with ~58% of total sales, while the South region with ~19% shows room for growth.
• Top 5 States (CA, NY, TX, PA, OH) contribute ~54% of sales, with CA alone driving ~21%, showing strong regional concentration.

➔ Impact

• Enabled real-time insights through Power BI dashboards with automatic daily refresh.
• Reduced daily data update time from hours to under a minute (average ~40 sec) using GitHub Actions.
• Delivered a reliable, low-latency, fully automated data pipeline with zero manual intervention.
• Achieved 100% workflow reliability as recorded in the GitHub Actions, with zero pipeline failures since deployment.

➔ Problem

• With the rise of streaming services, viewers now have access to thousands of movies across platforms.
• As a result, many viewers spend more time browsing than actually watching.
• This problem can lead to frustration, lower satisfaction and less time spent on the platform.
• Ultimately, this impacts both user experience and business performance.

➔ Solution

• Built a content-based movie recommender system trained on 5,000+ movie metadata records.
• Generated the top 5 similar titles for any selected movie in under 3 seconds.
• Integrated the TMDB API to dynamically fetch and display movie posters, enhancing user experience.
• Deployed the system as a Streamlit web app, used by 100+ users to discover personalized movie suggestions.

➔ Impact

• If this system gets scaled and integrated with a streaming service, this could :
  • Reduce the time users spend choosing what to watch.
  • Increase user engagement, watch time and customer satisfaction.
  • Help streaming platforms retain users by offering better personalized content.

➔ Problem Statement

• To analyze Netflix content data, uncovering valuable insights into how the platform evolves over time.

➔ Some Key Findings

• Cleaned and analyzed a dataset of 8,000+ Netflix Movies and TV Shows.
• More than 60% of the content on Netflix is rated for mature audiences.
  • Suggests that Netflix targets adult viewers to boost engagement and retention.
• More than 25% of the Movies and TV Shows were released on 1st day of the month.
  • Shows a consistent release schedule, likely aligned with subscription renewal cycles.
• More than 40% of the content on Netflix is exclusive to United States.
  • Shows a strong focus on U.S. market and content availability by location.
• More than 20% of the content on Netflix falls under the "Drama" genre.
  • Confirms that "Drama" is a key part of Netflix's content library.
• More than 23% of the content on Netflix was released in 2019 alone.
  • Indicates a major content push that year, possibly tied to growth or user acquisition efforts.

➔ Problem Statement

• To analyze Supermarket Sales data, identifying key factors for improving profitability and operational efficiency.

➔ Some Key Findings

• Analyzed purchasing patterns of 9,000+ customers of a Supermarket.
• More than 15% of the products sold were Snacks.
  • Shows that Snacks are a convenient choice and a major source of revenue.
• More than 32% of total sales came from the West region of the Supermarket.
  • Suggests that West region is a strong performing area as compared to others.
• Health and Soft drinks were the most profitable sub-categories in Beverages.
  • Shows that both type of drink options perform well among customers.
• November was the most profitable month contributing about 15% of the total annual profits.
  • Makes it an ideal time for running promotions and special offers.