Daksh Patel — Portfolio

Projekte

Zertifiziert

Selbstgesteuertes Projekt

Machine Learning for Automotive

KI / ML · August 2026

88/ 100

Eine ProoV-Fallstudie · Lernprojekt, kein Arbeitsverhältnis

Built an end-to-end used-car pricing analysis for VW and Audi listings in the UK market. The work combined exploratory analysis, data cleaning, feature engineering, and model comparison, then translated the results into a CPO pricing recommendation. It showed strong practical judgment by using Random Forest as the preferred model and explaining the business impact in terms leadership could act on.

Bewertet nach

Exploratory Data Analysis20%
Feature Engineering25%
Model Building & Evaluation35%
Business Communication20%

Bestanden · Bestehensgrenze 60/100

Was herausstach6

Combined VW and Audi listings correctly and used brand-aware EDA to surface the premium gap between the two marques.
Identified and removed clearly invalid rows such as zero-engine-size and extreme price outliers before modeling.
Compared Linear Regression and Random Forest using R², MAE, and RMSE, and reported a substantial improvement for the tree model.
Connected model output to CPO decision-making by estimating pricing exposure and recommending a practical deployment path.
Leakage-Free Feature Engineering
Comparative Model Evaluation

Meine eingereichte Arbeit10 Aufgaben

5 Aufgaben · 6 Zeilen · 5 Textantworten · 189 Wörter

VW Sprint1 Complete56 Zeichen
VW Sprint2 Complete61 Zeichen
VW Sprint3 Complete59 Zeichen
VW Business Insights1.5k Zeichen
Jupyterlite Code2 Zeilen
VW Sprint1 Complete1 Wort
VW Sprint2 Complete1 Wort
VW Sprint3 Complete1 Wort
VW Business Insights185 Wörter
Jupyterlite Code1 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.

Verifiziertes ZertifikatFälschungssicher · ausgestellt von ProoV

Zertifiziert

Selbstgesteuertes Projekt

Energy and Renewable: Machine Learning for the Power Grid

Junior Machine Learning Engineer · KI / ML · August 2026

84/ 100

Eine ProoV-Fallstudie · Lernprojekt, kein Arbeitsverhältnis

Built a TEY prediction model for gas-turbine operations using leakage-free sensor features and a time-based held-out evaluation. Compared a LinearRegression baseline with a RandomForest model, reported honest MAE/RMSE/R² on unseen data, and documented the model’s intended use, limitations, and monitoring plan in a concise model card.

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 measured downstream of the prediction moment
Compared a linear baseline against a tree ensemble and showed a meaningful MAE improvement
Reported held-out MAE, RMSE, and R² and included a residual summary instead of relying on a single flattering metric
Wrote a model card that states intended use, limitations, and a concrete monitoring plan
Leakage-Free Feature Selection
Held-Out Model Evaluation

Meine eingereichte Arbeit20 Aufgaben

12 Aufgaben · 13 Zeilen · Python, JavaScript · 8 Textantworten · 427 Wörter

Problem Frame224 Zeichen
Leakage Flags113 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 Evaluate130 Zeichen
Residual Read271 Zeichen
Drift Monitor92 Zeichen
Model Card1.3k Zeichen
Teach BackJavaScript · 699 Zeichen
Problem Frame17 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

Verifiziertes ZertifikatFälschungssicher · ausgestellt von ProoV

Zertifiziert

Selbstgesteuertes Projekt

AI-Assisted Code Modernization with IBM

Junior Software Engineer · Softwareentwicklung · August 2026

96/ 100

Basierend auf einer öffentlichen Fallstudie von IBM · nicht mit IBM verbunden

Built and verified a full legacy-service repair: fixed the wear calculation with true division, handled missing service readings safely, corrected the fleet report’s crash and average, and preserved the 15,000 km / 80% business rules. Also added the missing regression test, documented the agent’s mistakes in NOTES.md, and delivered a data-driven breakdown-risk analysis that ranks cars by the factors the dataset actually supports.

Bewertet nach

Fix and extend the repo with the agent35%
Diagnose the bug20%
Direct and audit the AI agent25%
Explain it like an engineer20%

Bestanden · Bestehensgrenze 60/100

Was herausstach6

Correctly identified the floor-division bug and explained why it suppressed a nearly-worn car to 0%
Caught the agent’s planted mistakes, including the stray syntax-breaking character and the threshold change
Wrote a concrete acceptance checklist and used verify.py plus pytest to confirm the fix
Produced an analysis that explicitly rejects the misleading mileage/age assumption and ranks risk from the real predictors
Leakage-Free Bug Diagnosis
Verified AI Output Auditing

Das Ergebnis

Zum CodeDaksh1308 / proov-km-waechter-fix

Meine eingereichte Arbeit19 Aufgaben

11 Aufgaben · 2.7k Zeichen · Python · 8 Textantworten · 102 Wörter

Bob Trial Click198 Zeichen
Bob Ready60 Zeichen
Diagnose Line130 Zeichen
Diagnose Why67 Zeichen
Audit Findings158 Zeichen
Audit Why284 Zeichen
Acceptance ChecklistPython · 235 Zeichen
Template Repo Click82 Zeichen
Exec Pitch884 Zeichen
Bob Bonus514 Zeichen
Repo URL54 Zeichen
Bob Trial Click1 Wort
Bob Ready1 Wort
Diagnose Line10 Wörter
Diagnose Why11 Wörter
Audit Findings1 Wort
Audit Why41 Wörter
Acceptance Checklist36 Wörter
Template Repo Click1 Wort

Verifiziertes ZertifikatFälschungssicher · ausgestellt von ProoV