What A.H.A demonstrated

Built a leakage-aware gas-turbine TEY predictor end to end: selected the correct sensor inputs, excluded downstream CO/NOx emissions, trained a LinearRegression baseline and a RandomForest model, and validated on a locked-away later-year test split. The final model was evaluated honestly with held-out MAE, RMSE, R2, and a residual read, and the submission includes a concise model card and manager-friendly explanation of when the model should and should not be trusted.

• Leakage-Free Feature Selection
• Time-Based Holdout Validation
• Baseline-vs-Ensemble Comparison
• Honest Held-Out Evaluation