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: selected the 8 available sensor features, excluded downstream CO/NOx emissions, trained both a linear baseline and a random forest, and validated on a locked-away later-year test split. The final model achieved about 1.5 MWh MAE and was documented with a concise model card covering intended use, limitations, and monitoring.
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
- Dropped CO and NOx explicitly because they are downstream emissions and unavailable at prediction time
- Used an earlier-years train / later-years test split instead of a random shuffle
- Compared LinearRegression against RandomForest and showed a clear held-out improvement
- Included residual analysis plus a concrete rolling-MAE retraining trigger
- Leakage-Free Feature Engineering
- Honest Held-Out Evaluation
The work I submitted18 tasks
10 tasks · 11 lines · Python, JavaScript · 8 written answers · 487 words
- 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 Evaluate131 characters
- Residual Read417 characters
- Drift Monitor92 characters
- Teach BackJavaScript · 801 characters
- Model Card1.6k characters
- Train Validate Baseline141 words
- Train Validate Forest76 words
- Train Validate1 word
- Tune Evaluate Setup110 words
- Tune Evaluate Residuals92 words
- Tune Evaluate1 word
- Residual Read65 words
- Drift Monitor1 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.