What Aayush demonstrated

Built an end-to-end TEY prediction workflow for a gas-turbine plant using leakage-free sensor features and a time-based train/test split. Compared a LinearRegression baseline with a RandomForest model, selected the stronger tree ensemble on held-out performance, and documented the result with honest MAE/RMSE/R² plus a monitoring plan for drift and retraining.

• Leakage-Free Feature Selection
• Honest Held-Out Evaluation
• Model Comparison and Calibration
• Operational Risk Awareness