Self-directed project
Energy and Renewable: Machine Learning for the Power Grid
Junior Machine Learning Engineer · AI / ML · September 2026
A ProoV case study · educational project, not employment
Built a turbine energy-yield predictor end to end: framed TEY as the target, used a time-based holdout, compared LinearRegression against a RandomForest, and reported honest held-out MAE/RMSE/R². The accompanying model card explains the feature choices, why CO/NOx were excluded, the plant-specific limits, and a practical monitoring plan for drift.
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
- Used a genuinely time-based split with earlier data for training and later data held out for testing.
- Compared a linear baseline against a tree ensemble and showed a clear held-out MAE improvement.
- Reported held-out MAE, RMSE, and R² and gave a plain-language explanation of the model’s main failure mode.
- Leakage-Aware Problem Framing
- Held-Out Evaluation Discipline
- Model Card Communication
The work I submitted19 tasks
11 tasks · 6.7k characters · Python, JavaScript · 8 written answers · 294 words
- Problem Frame160 characters
- Leakage Flags114 characters
- Train Validate BaselinePython · 922 characters
- Train Validate Forest943 characters
- Train Validate124 characters
- Tune Evaluate SetupPython · 1.5k characters
- Tune Evaluate91 characters
- Residual Read242 characters
- Drift Monitor95 characters
- Model Card1.8k characters
- Teach BackJavaScript · 805 characters
- Problem Frame11 words
- Leakage Flags1 word
- Train Validate Baseline61 words
- Train Validate Forest76 words
- Train Validate1 word
- Tune Evaluate Setup110 words
- Tune Evaluate1 word
- Residual Read33 words
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.