Certified
Self-directed project
Energy and Renewable: Machine Learning for the Power Grid
Junior Machine Learning Engineer · AI / ML · September 2026
92/ 100
A ProoV case study · educational project, not employment
Built an end-to-end turbine yield predictor using leakage-free sensor inputs and a genuine time-based holdout. Compared a LinearRegression baseline with a tuned RandomForest, evaluated on held-out MAE/RMSE/R2, and documented the model’s intended use, limits, and drift-monitoring plan 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 excluded CO and NOx as downstream leakage features and explained why they were not available at prediction time.
- Used a genuine time-based split instead of a random shuffle, with the later period locked away for testing.
- Compared a LinearRegression baseline against a RandomForest and showed a clear held-out improvement in MAE and R2.
- Included a residual read and a monitoring plan that focuses on input-range drift and rising rolling error.
- Leakage-Free Feature Selection
- Honest Held-Out Evaluation
The work I submitted20 tasks
12 tasks · 13 lines · Python, JavaScript · 8 written answers · 434 words
- Problem Frame169 characters
- Leakage Flags113 characters
- Train Validate BaselinePython · 1.4k characters
- Train Validate Forest944 characters
- Train Validate124 characters
- Tune Evaluate SetupPython · 1.5k characters
- Tune Evaluate ResidualsPython · 2 lines
- Tune Evaluate132 characters
- Residual Read413 characters
- Drift Monitor93 characters
- Model Card1.2k characters
- Teach BackJavaScript · 768 characters
- Problem Frame11 words
- Leakage Flags1 word
- Train Validate Baseline141 words
- Train Validate Forest77 words
- Train Validate1 word
- 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.