Key Influencing Factors of Used Car Prices Driven by Machine Learning and Price Prediction

Research on Price Prediction and Influencing Factors of Used Car Prices Based on Machine Learning Algorithms: Addressing the core issue of opaque pricing in the current used car market, this study utilized real car data, linear regression, and random forest among other machine learning methods to achieve precise price prediction and analysis of related influencing factors. During the research process, many distribution charts were used to more intuitively compare the correlations among multiple variables. The results show that the random forest model has superior predictive performance, with an R coefficient reaching 0.9264. Through the analysis of feature importance, it was found that vehicle age and mileage are the most significant factors influencing the price of used cars, and their importance is significantly higher than that of other vehicle characteristics. This study provides a scientific pricing basis for used car transactions, effectively enhancing the fairness and transparency of the transactions, but there are still some shortcomings: the diversity of data needs to be strengthened, and the stability of the model's prediction needs to be addressed. The absence of these models' explainability is the crucial factor that leads to the discrepancy between theoretical research and practical operation analysis.