Self-directed project
Machine Learning for Automotive
AI / ML · July 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, trained and compared Linear Regression and Random Forest models, and translated the results into a CPO pricing recommendation. The work includes quantified model gains, feature-driver interpretation, and a clear note on where the current data still limits rollout.
Graded against
- Exploratory Data Analysis20%
- Feature Engineering25%
- Model Building & Evaluation35%
- Business Communication20%
Passed · pass mark 60/100
What stood out6
- Combined VW and Audi listings into a single analysis frame with a brand indicator and used it consistently in EDA
- Built a baseline Linear Regression on mileage only, then moved to richer features and compared against Random Forest
- Interpreted the model results in business terms, including pricing error reduction and portfolio-level mispricing exposure
- Called out a real deployment gap: the current dataset lacks a brand field, limiting premium-brand pricing logic
- Exploratory Data Analysis
- Leakage-Free Feature Engineering
The work I submitted10 tasks
5 tasks · 6 lines · 5 written answers · 192 words
- VW Sprint1 Complete56 characters
- VW Sprint2 Complete61 characters
- VW Sprint3 Complete59 characters
- VW Business Insights1.4k characters
- Jupyterlite Code2 lines
- VW Sprint1 Complete1 word
- VW Sprint2 Complete1 word
- VW Sprint3 Complete1 word
- VW Business Insights188 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.