Certified
Self-directed project
Energy and Renewable: Machine Learning for the Power Grid
Junior Machine Learning Engineer · AI / ML · September 2026
84/ 100
A ProoV case study · educational project, not employment
Built a TEY prediction workflow for gas-turbine data using a leakage-free feature set and a genuine time-based holdout. Compared LinearRegression with a RandomForest, reported held-out MAE/RMSE/R2, and added a residual read plus a concise model card covering intended use, exclusions, limitations, and monitoring.
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 cannot be used at prediction time.
- Compared a linear baseline with a tree ensemble and judged performance on held-out data rather than training fit.
- Reported MAE, RMSE, and R2 on the locked-away test set and checked residual behavior for bias/variance concerns.
- Explained the model in manager-friendly language, including what it predicts, how accurate it is, and when it would fail.
- Leakage-Free Feature Selection
- Held-Out Time-Based Evaluation
The work I submitted20 tasks
12 tasks · 13 lines · Python, JavaScript · 8 written answers · 413 words
- Problem Frame116 characters
- Leakage Flags113 characters
- Train Validate BaselinePython · 1.4k characters
- Train Validate Forest942 characters
- Train Validate125 characters
- Tune Evaluate SetupPython · 1.5k characters
- Tune Evaluate ResidualsPython · 2 lines
- Tune Evaluate129 characters
- Residual Read228 characters
- Drift Monitor93 characters
- Model Card685 characters
- Teach BackJavaScript · 674 characters
- Problem Frame3 words
- Leakage Flags1 word
- Train Validate Baseline141 words
- Train Validate Forest76 words
- Train Validate1 word
- Tune Evaluate Setup110 words
- Tune Evaluate Residuals80 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.