Selbstgesteuertes Projekt
Energy and Renewable: Machine Learning for the Power Grid
Junior Machine Learning Engineer · KI / ML · September 2026
Eine ProoV-Fallstudie · Lernprojekt, kein Arbeitsverhältnis
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.
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 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
Meine eingereichte Arbeit20 Aufgaben
12 Aufgaben · 13 Zeilen · Python, JavaScript · 8 Textantworten · 413 Wörter
- Problem Frame116 Zeichen
- Leakage Flags113 Zeichen
- Train Validate BaselinePython · 1.4k Zeichen
- Train Validate Forest942 Zeichen
- Train Validate125 Zeichen
- Tune Evaluate SetupPython · 1.5k Zeichen
- Tune Evaluate ResidualsPython · 2 Zeilen
- Tune Evaluate129 Zeichen
- Residual Read228 Zeichen
- Drift Monitor93 Zeichen
- Model Card685 Zeichen
- Teach BackJavaScript · 674 Zeichen
- Problem Frame3 Wörter
- Leakage Flags1 Wort
- Train Validate Baseline141 Wörter
- Train Validate Forest76 Wörter
- Train Validate1 Wort
- Tune Evaluate Setup110 Wörter
- Tune Evaluate Residuals80 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.