Second-hand car price prediction based on multiple linear regression models

Abstract

With the advancement of the automotive manufacturing industry and the convenience of public transportation, the second-hand car market continues to expand. To comprehensively evaluate the price of used cars considering various factors, there is an urgent need for a computational model based on big data and machine learning. This article aims to fulfill this requirement, this article introduces a multiple linear regression model based on machine learning technology, which is applied to predict the prices of second-hand cars. In this study, the author digitized categorical variables and removed factors irrelevant to numerical variables using a dataset containing nearly 1500 samples from the second-hand car market. By constructing a multiple linear regression model with independent variables such as insurance validity, fuel_type, seats, ownership, transmission, mileage (kmpl), engine (cc), kms_driven and registration year with price (unit: ten thousand) as dependent variable. The root mean square error (RMSE) was finally obtained as 13.939.