Self-directed project
Energy and Renewable: Machine Learning for the Power Grid
Junior Machine Learning Engineer · AI / ML · August 2026
A ProoV case study · educational project, not employment
Built a leakage-aware 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 evaluated on a locked-away later-year test split. The final model achieved 1.50 MWh MAE, 1.908 RMSE, and 0.9838 R² on held-out data, with a model card that clearly states limits, drift risks, and monitoring triggers.
Graded against
- Build and validate the model correctly35%
- Optimize and evaluate honestly25%
- Write the Model Card (clarity + honesty)25%
- Explain it to a non-expert15%
Passed · pass mark 60/100
What stood out6
- Correctly excluded CO and NOX as downstream leakage features and explained why they are unavailable at prediction time
- Used a time-based split with earlier years for training and later years locked away for testing
- Compared a linear baseline to a tuned RandomForest and reported held-out MAE, RMSE, and R²
- Included a residual read and a monitoring plan that acknowledges drift and retraining triggers
- Leakage-Free Feature Selection
- Honest Held-Out Evaluation
The work I submitted20 tasks
12 tasks · 13 lines · Python, JavaScript · 8 written answers · 424 words
- Problem Frame113 characters
- Leakage Flags114 characters
- Train Validate BaselinePython · 1.4k characters
- Train Validate Forest943 characters
- Train Validate124 characters
- Tune Evaluate SetupPython · 1.5k characters
- Tune Evaluate ResidualsPython · 2 lines
- Tune Evaluate132 characters
- Residual Read164 characters
- Drift Monitor94 characters
- Model Card1.2k characters
- Teach BackJavaScript · 735 characters
- Problem Frame2 words
- Leakage Flags1 word
- Train Validate Baseline141 words
- Train Validate Forest76 words
- Train Validate1 word
- Tune Evaluate Setup110 words
- Tune Evaluate Residuals92 words
- Tune Evaluate1 word
Summarised on purpose — the submitted code and writing stay private so this page cannot be reused as an answer key. The full submission sits behind the verified certificate.