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

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

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

{"text":"To: VP of Used Car Sales\n\nThe Random Forest model outperformed the Linear Regression model for used-car price prediction. It achieved an R² score of 0.9504 and a Mean Absolute Error (MAE) of £1,438, compared to Linear Regression's R² of 0.8328 and MAE of £2,622. This demonstrates that Random Forest provides more accurate vehicle valuations and is the preferred model for pricing decisions.\n\nThe three most important factors affecting resale value were MPG, car age, and engine size. Vehicles with higher fuel efficiency tend to retain more value because they are cheaper to operate. Newer vehicles command higher prices because depreciation increases with age. Larger engines also tend to achieve higher resale values due to stronger performance and market demand.\n\nThe model predicted a resale value of £9,874 for a 2018 VW Golf and £14,809 for a 2018 Audi A4. This represents an Audi premium of £4,935, supporting the findings from the exploratory analysis that premium brands maintain stronger resale values.\n\nFrom a business perspective, an MAE of £1,438 means the average pricing error is approximately £1,438 per vehicle. Across 100,000 used cars annually, this represents pricing risk of roughly £143.8 million.\n\nRecommendation: Deploy the Random Forest model within the CPO pricing process to support acquisition and resale decisions. Regular retraining with updated market data is recommended to maintain accuracy and profitability.","charCount":1445,"selfChecks":[{"label":"Model comparison","checked":false},{"label":"Top features identified","checked":false},{"label":"Financial Impact","checked":false},{"label":"Clear recommendation","checked":false}]}

base64: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
…