What siddhi demonstrated

Built an end-to-end TEY predictor for gas-turbine data using leakage-free sensor features and a genuine time-based holdout. Compared a LinearRegression baseline with a tuned RandomForest, evaluated on unseen later-period data with MAE, RMSE, and R², and documented the model’s intended use, limits, and drift-monitoring plan in a concise model card.

• Leakage-Free Feature Selection
• Time-Based Validation
• Honest Held-Out Evaluation
• Plain-Language Model Communication