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 a regression target, excluded downstream CO/NOx emissions, and validated on a locked later-period test split. Compared a LinearRegression baseline with a tuned RandomForest, then reported held-out MAE, RMSE, R2, and residual behavior to show the model’s real performance and limits.
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 emission outputs and kept the 8 legitimate sensor features.
- Used an earlier-years train / later-years test split instead of a random shuffle, preserving time order.
- Compared a LinearRegression baseline against a RandomForest and showed a clear held-out MAE improvement.
- Reported held-out MAE, RMSE, R2, and a residual summary rather than relying on a single flattering metric.
- Leakage-Free Feature Selection
- Honest Held-Out Evaluation
The work I submitted19 tasks
11 tasks · 12 lines · Python · 8 written answers · 358 words
- Problem Frame129 characters
- Leakage Flags113 characters
- Train Validate BaselinePython · 1.0k characters
- Train Validate Forest1.1k characters
- Train Validate124 characters
- Tune Evaluate SetupPython · 1.5k characters
- Tune Evaluate ResidualsPython · 2 lines
- Tune Evaluate130 characters
- Residual Read250 characters
- Drift Monitor93 characters
- Model Card863 characters
- Problem Frame6 words
- Leakage Flags1 word
- Train Validate Baseline79 words
- Train Validate Forest80 words
- Train Validate1 word
- Tune Evaluate Setup110 words
- Tune Evaluate Residuals80 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.