Overview
This project was part of the Machine Learning Practice course at IIT Madras. The objective was to predict the total purchase amount for individual user sessions on a large-scale e-commerce platform — a classic regression problem with real business impact.
Approach
- Performed exploratory data analysis to understand session-level features
- Applied feature engineering to capture behavioral patterns
- Trained and evaluated regression models using Scikit-learn
Tech Stack
- Python — core language
- Pandas — data manipulation and EDA
- Scikit-learn — model training and evaluation
- Kaggle — dataset and competition platform