This project successfully applies data science techniques to explore and predict used Ford car prices. The insights gained can inform Ford's product development, pricing strategies, and marketing efforts, as well as guide consumers in making informed purchasing decisions.
Statistical Tests:
Chi-Squared Test: Analyzed the association between car model and transmission type. T-Test: Compared the mean mpg across petrol and diesel cars. One-Way ANOVA: Evaluated differences in mean prices across different fuel types. Predictive Modeling:
Initial Regression: A basic linear regression model was built to predict car prices. Ridge Regression: An improved model using Ridge Regression was developed, with hyperparameter tuning to enhance the accuracy of the predictions. Insights:
The analysis highlighted key factors influencing Ford car prices, such as the car's age and engine size. The predictive model was particularly accurate for lower-priced cars, offering valuable insights for both Ford and potential car buyers.