Abstract:

At the outset, there is a manufacturerset price for vehicles that are particular to brand, model, year, and features. As they get older and are sold as used goods, their value is affected by market forces related to their unique characteristics, as well as their personal background. It gets more difficult to use traditional ways to evaluate their worth when they are more unique in comparison to comparable autos. A more precise evaluation of a vehicle's value is possible with the use of Machine Learning (ML) algorithms that make better use of data on all of the less common automotive qualities. This study examines the effectiveness of several Machine Learning (ML) algorithms in predicting the values of used vehicles. These algorithms include Linear Regression, Ridge Regression, Lasso Regression, and Random Forest Regression. To better use previous data in projecting current prices, an effective price prediction algorithm must be able to integrate depreciation. An big public dataset consisting of used autos was analyzed for this research project. Used cars, regression analysis, depreciation, supervised ML systems for price prediction

Description:

.