Self-directed project
Machine Learning for Automotive
AI / ML · September 2026
A ProoV case study · educational project, not employment
Built an end-to-end used-car pricing workflow for VW and Audi listings: combined the datasets, engineered age and mileage-per-year features, trained and compared Linear Regression and Random Forest models, and tuned the forest with GridSearchCV. The final write-up translated model performance and feature importance into a practical CPO pricing recommendation with example price estimates for a VW Golf and Audi A4.
Graded against
- Exploratory Data Analysis20%
- Feature Engineering25%
- Model Building & Evaluation35%
- Business Communication20%
Passed · pass mark 60/100
What stood out6
- Engineered the required car_age and mileage_per_year features and aligned new-car inference columns to the training matrix.
- Compared Linear Regression against Random Forest using all three requested metrics and then extended the work with GridSearchCV tuning.
- Interpreted the model outputs in business terms, including a concrete pricing recommendation for the CPO workflow.
- Leakage-Free Feature Engineering
- Honest Model Evaluation
- Model Comparison and Tuning
The work I submitted6 tasks
3 tasks · 4 lines · 3 written answers · 178 words
- VW Sprint3 Complete59 characters
- VW Business Insights1.5k characters
- Jupyterlite Code2 lines
- VW Sprint3 Complete1 word
- VW Business Insights176 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.