About

This canvas implements an end-to-end machine learning pipeline that loads chocolate sales data, cleans it, engineers features (temporal, derived, and categorical encodings), trains a Random Forest regressor to predict revenue, and visualizes model performance through predicted vs actual scatter plots, residual distributions, and feature importance rankings. The workflow demonstrates a complete predictive analytics solution with rigorous train/test evaluation metrics (R², RMSE, MAE) and cross-validation validation.