This project aims to compare and contrast Principal Component Regression (PCR) and Partial Least Squares Regression (PLS) using the Air Quality Dataset. The dataset includes measurements of various air pollutants and meteorological variables. The primary objective is to evaluate the performance of PCR and PLS in handling multicollinearity and reducing dimensionality to predict benzene (C6H6) concentrations. The analysis includes data cleaning, outlier handling, and implementation of both regression techniques. Performance metrics such as RMSE and R-squared are used to compare the models, highlighting the strengths and weaknesses of each approach.

The project compares Ridge and Lasso regression models to predict college graduation rates using the College dataset. It explores the differences in regularization techniques, evaluates predictive performance, and analyzes feature importance for both models.