What Arunkumar demonstrated

Built a turbine TEY predictor end to end using leakage-free sensor features, a LinearRegression baseline, and a tuned RandomForest. Evaluated on a locked-away later time period, the model achieved MAE 1.532 MWh, RMSE 1.937 MWh, and R² 0.9833, and the candidate documented the model’s intended use, limits, and monitoring plan in a concise model card.

• Leakage-Free Feature Selection
• Held-Out Model Evaluation
• Residual-Based Error Reading
• Plain-Language Model Communication