What Ishita demonstrated

Built a leakage-free turbine yield predictor end to end: framed TEY as the target, excluded downstream CO/NOx emissions, trained a LinearRegression baseline and a RandomForest model, and validated on a chronological held-out split. Reported honest held-out performance (MAE, RMSE, R²), checked residual behavior, and documented intended use, limitations, and monitoring guidance in a model card.

• Leakage-Free Feature Selection
• Chronological Holdout Validation
• Honest Held-Out Evaluation
• Plain-Language Model Communication