End-to-end machine learning pipelines — from data ingestion to model deployment.
A complete supervised learning pipeline for predicting residential property prices. Covers data ingestion and cleaning, exploratory data analysis, feature engineering (encoding, scaling, outlier handling), training and comparing multiple regression models (Linear, Ridge, Lasso, Random Forest, XGBoost), hyperparameter tuning with cross-validation, and evaluation using RMSE and R². Structured as a reproducible, modular codebase following MLOps best practices.
Explore physics and materials-science research projects:
View STEM Projects