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 an end-to-end TEY predictor for a gas turbine using leakage-free sensor features and a genuine time-based holdout. Compared a LinearRegression baseline with a tuned RandomForest, then evaluated the final model on held-out data with MAE, RMSE, R2, and a residual read. Also wrote a concise model card explaining intended use, excluded leakage features, limitations, and drift 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 dropped CO and NOx because they are downstream emission outputs not available at prediction time.
- Used an earlier-years/later-years split to keep the test set genuinely held out.
- Reported held-out MAE, RMSE, and R2 for the tuned forest and compared it against a linear baseline.
- Noted residual behavior and acknowledged that strong R2 does not prove generalization beyond this plant.
- Leakage-Free Feature Selection
- Honest Time-Based Evaluation
Meine eingereichte Arbeit20 Aufgaben
12 Aufgaben · 13 Zeilen · Python, JavaScript · 8 Textantworten · 480 Wörter
- Problem Frame163 Zeichen
- Leakage Flags113 Zeichen
- Train Validate BaselinePython · 1.4k Zeichen
- Train Validate Forest943 Zeichen
- Tune Evaluate SetupPython · 1.5k Zeichen
- Tune Evaluate ResidualsPython · 2 Zeilen
- Tune Evaluate130 Zeichen
- Residual Read299 Zeichen
- Drift Monitor93 Zeichen
- Train Validate124 Zeichen
- Model Card838 Zeichen
- Teach BackJavaScript · 714 Zeichen
- Problem Frame12 Wörter
- Leakage Flags1 Wort
- Train Validate Baseline141 Wörter
- Train Validate Forest76 Wörter
- Tune Evaluate Setup110 Wörter
- Tune Evaluate Residuals92 Wörter
- Tune Evaluate1 Wort
- Residual Read47 Wörter
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.