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-yield predictor end to end: framed TEY as the target, removed downstream CO/NOx leakage features, trained a LinearRegression baseline and a RandomForest model, and validated on a locked-away later time period. Reported held-out MAE, RMSE, and R², checked residual behavior, and documented practical limits and drift monitoring in a model card written for operational use.
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 because they are measured downstream of the prediction point
- Used an earlier-period train / later-period test split instead of a random shuffle
- Reported held-out MAE, RMSE, and R² and inspected residuals for bias
- Explained the model to a non-technical manager in clear, accurate language
- Leakage-Free Feature Selection
- Time-Based Holdout Evaluation
The work I submitted20 tasks
12 tasks · 13 lines · Python, JavaScript · 8 written answers · 319 words
- Problem Frame138 characters
- Leakage Flags113 characters
- Tune Evaluate SetupPython · 1.5k characters
- Tune Evaluate ResidualsPython · 2 lines
- Tune Evaluate132 characters
- Residual Read254 characters
- Drift Monitor91 characters
- Train Validate Forest943 characters
- Train Validate BaselinePython · 1.4k characters
- Train Validate125 characters
- Model Card2.4k characters
- Teach BackJavaScript · 779 characters
- Problem Frame6 words
- Leakage Flags1 word
- Tune Evaluate Setup110 words
- Tune Evaluate Residuals92 words
- Tune Evaluate1 word
- Residual Read32 words
- Drift Monitor1 word
- Train Validate Forest76 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.