{"completed":true,"notebookName":"vw_sprint1_eda.ipynb"}

{"completed":true,"notebookName":"vw_sprint2_features.ipynb"}

{"completed":true,"notebookName":"vw_sprint3_models.ipynb"}

{"text":"I compared two models to predict used car prices: Linear Regression and a Tuned Random Forest. The Tuned Random Forest performed better, achieving an R² score of 0.9516 compared with 0.8328 for Linear Regression. It also reduced the average prediction error (MAE) from £2,621.62 to £1,420.82, making it the most accurate model developed in this project.\n\nThe model identified fuel efficiency (MPG), vehicle age, and engine size as the three biggest factors affecting resale price. Mileage and fuel type also influenced prices but had a smaller impact. These results matched the trends observed during the exploratory data analysis.\n\nWith an average prediction error of £1,420.82 per vehicle, pricing around 100,000 used cars each year represents approximately £142 million of pricing exposure across the portfolio. Improving pricing accuracy can therefore reduce costly overpricing and underpricing.\n\nBased on these findings, I recommend that the CPO team adopts the Tuned Random Forest model as the standard pricing tool. It provides more consistent vehicle valuations than the baseline model, supports faster data-driven pricing decisions, and can help improve profitability while increasing customer confidence.","charCount":1214,"selfChecks":[{"label":"Model comparison","checked":true},{"label":"Top features identified","checked":false},{"label":"Financial Impact","checked":false},{"label":"Clear recommendation","checked":false}]}

base64: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
…