Selbstgesteuertes Projekt
Energy and Renewable: Machine Learning for the Power Grid
Junior Machine Learning Engineer · KI / ML · August 2026
Eine ProoV-Fallstudie · Lernprojekt, kein Arbeitsverhältnis
Built a leakage-aware turbine yield predictor end to end: framed TEY as the target, excluded downstream CO/NOX emissions, trained a LinearRegression baseline and a RandomForest model, and evaluated on a locked-away later-year test split. The final model achieved 1.50 MWh MAE, 1.908 RMSE, and 0.9838 R² on held-out data, with a model card that clearly states limits, drift risks, and monitoring triggers.
Bewertet nach
- Build and validate the model correctly35%
- Optimize and evaluate honestly25%
- Write the Model Card (clarity + honesty)25%
- Explain it to a non-expert15%
Bestanden · Bestehensgrenze 60/100
Was herausstach6
- Correctly excluded CO and NOX as downstream leakage features and explained why they are unavailable at prediction time
- Used a time-based split with earlier years for training and later years locked away for testing
- Compared a linear baseline to a tuned RandomForest and reported held-out MAE, RMSE, and R²
- Included a residual read and a monitoring plan that acknowledges drift and retraining triggers
- Leakage-Free Feature Selection
- Honest Held-Out Evaluation
Meine eingereichte Arbeit20 Aufgaben
12 Aufgaben · 13 Zeilen · Python, JavaScript · 8 Textantworten · 424 Wörter
- Problem Frame113 Zeichen
- Leakage Flags114 Zeichen
- Train Validate BaselinePython · 1.4k Zeichen
- Train Validate Forest943 Zeichen
- Train Validate124 Zeichen
- Tune Evaluate SetupPython · 1.5k Zeichen
- Tune Evaluate ResidualsPython · 2 Zeilen
- Tune Evaluate132 Zeichen
- Residual Read164 Zeichen
- Drift Monitor94 Zeichen
- Model Card1.2k Zeichen
- Teach BackJavaScript · 735 Zeichen
- Problem Frame2 Wörter
- Leakage Flags1 Wort
- Train Validate Baseline141 Wörter
- Train Validate Forest76 Wörter
- Train Validate1 Wort
- Tune Evaluate Setup110 Wörter
- Tune Evaluate Residuals92 Wörter
- Tune Evaluate1 Wort
Bewusst zusammengefasst — der eingereichte Code und die Texte bleiben privat, damit diese Seite nicht als Lösungsvorlage dient. Die vollständige Einreichung steht hinter dem verifizierten Zertifikat.