Tooba Nadeem Ali completed Energy and Renewable: Machine Learning for the Power Grid

Built an end-to-end turbine yield predictor using leakage-free sensor inputs and a genuine time-based split. The candidate benchmarked a LinearRegression baseline against a tuned RandomForest, evaluated on held-out later-period data, and reported honest error metrics (MAE 1.532 MWh, RMSE 1.937 MWh, R² 0.9833). They also authored a practical model card that explains feature exclusions, limitations, and monitoring in plain language.

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