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 turbine energy-yield regressor end to end on the UCI gas-turbine dataset: framed TEY as the target, excluded downstream CO/NOx leakage features, trained a LinearRegression baseline and a tuned RandomForest, and validated on a held-out later time period. Reported honest held-out MAE/RMSE/R² and documented deployment limits, drift risks, and a monitoring threshold in a concise model card.
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 dropped CO and NOx as downstream emissions features instead of using them for inflated performance
- Used a genuine time-based split and kept evaluation on locked-away later data
- Reported held-out MAE, RMSE, and R², then checked residual spread rather than relying on a single headline metric
- Wrote a model card that clearly states intended use, limitations, and a concrete drift-monitoring plan
- Leakage-Free Feature Selection
- Honest Held-Out Evaluation
The work I submitted19 tasks
11 tasks · 12 lines · Python · 8 written answers · 430 words
- Problem Frame149 characters
- Leakage Flags114 characters
- Train Validate BaselinePython · 1.4k characters
- Train Validate124 characters
- Train Validate Forest943 characters
- Tune Evaluate SetupPython · 1.5k characters
- Tune Evaluate ResidualsPython · 2 lines
- Tune Evaluate132 characters
- Residual Read301 characters
- Drift Monitor91 characters
- Model Card1.7k characters
- Problem Frame8 words
- Leakage Flags1 word
- Train Validate Baseline141 words
- Train Validate1 word
- Train Validate Forest76 words
- 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.