Suraj Panda completed Energy and Renewable: Machine Learning for the Power Grid

Built an end-to-end TEY prediction workflow for gas-turbine data using leakage-free sensor features and a genuine time-based holdout. Benchmarked LinearRegression against a tuned RandomForest, evaluated with held-out MAE/RMSE/R², and documented residual behavior and operating limits in a model card. The work shows solid judgment about data leakage, validation discipline, and communicating model performance to non-technical stakeholders.

• Leakage-Free Feature Engineering
• Honest Held-Out Evaluation
• Residual Diagnostics
• Plain-Language Model Communication