Self-directed project
Machine Learning for Automotive
AI / ML · October 2026
A ProoV case study · educational project, not employment
Built an end-to-end used-car pricing analysis for VW and Audi listings: combined the datasets, explored price and mileage patterns, engineered predictive features, and compared Linear Regression with Random Forest using R² and MAE. The work culminated in a business-facing recommendation to use the Random Forest as a decision-support tool for CPO pricing, with model outputs interpreted through feature importance and operational impact.
Graded against
- Exploratory Data Analysis20%
- Feature Engineering25%
- Model Building & Evaluation35%
- Business Communication20%
Passed · pass mark 60/100
What stood out6
- Built a clear VW-vs-Audi EDA with distributions, correlation heatmap, scatter plots, and brand-level price comparison.
- Identified engine size, car age, and mileage as key pricing drivers and connected them to the observed correlations.
- Compared Linear Regression against Random Forest using R² and MAE, and translated the results into a pricing recommendation for the CPO team.
- Exploratory Data Analysis Across Segmented Brands
- Leakage-Aware Feature Design
- Model Comparison Using Multiple Regression Metrics
The work I submitted10 tasks
5 tasks · 6 lines · 5 written answers · 175 words
- VW Sprint1 Complete56 characters
- VW Sprint2 Complete61 characters
- VW Sprint3 Complete59 characters
- VW Business Insights1.5k characters
- Jupyterlite Code2 lines
- VW Sprint1 Complete1 word
- VW Sprint2 Complete1 word
- VW Sprint3 Complete1 word
- VW Business Insights171 words
- Jupyterlite Code1 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.