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 leakage-free turbine yield predictor end to end: framed TEY as the target, used only the 8 available sensor inputs, trained a LinearRegression baseline and a tuned RandomForest, and validated on a locked later time period. The work reports honest held-out MAE/RMSE/R², includes residual analysis, and documents deployment limits, drift risks, and monitoring 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 are unavailable at prediction time.
- Used a time-based split (2011–2013 train, 2014–2015 test) instead of a random shuffle, preserving temporal validity.
- Reported held-out MAE, RMSE, and R², then read the residuals rather than stopping at a flattering headline metric.
- Wrote a model card that clearly states intended use, limitations, silent-drift failure mode, and a concrete monitoring plan.
- Leakage-Free Feature Selection
- Honest Held-Out Evaluation
The work I submitted20 tasks
12 tasks · 13 lines · Python, JavaScript · 8 written answers · 436 words
- Problem Frame172 characters
- Leakage Flags113 characters
- Train Validate BaselinePython · 1.4k characters
- Train Validate Forest943 characters
- Train Validate115 characters
- Tune Evaluate SetupPython · 1.5k characters
- Tune Evaluate ResidualsPython · 2 lines
- Tune Evaluate132 characters
- Residual Read324 characters
- Teach BackJavaScript · 881 characters
- Drift Monitor92 characters
- Model Card1.5k characters
- Problem Frame14 words
- Leakage Flags1 word
- Train Validate Baseline141 words
- Train Validate Forest76 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.