Smart Pricing: Machine Learning Approaches for the Used Automobile Industry

Local markets and online used automobile marketplaces have grown quickly in the modern era. Many interested parties in secondhand cars have lack a clear understanding about fair price. This paper mainly aims to develop or construct a predictive model for used car prices using machine learning algorithms. It offers accurate prices based on multiple aspects including brand, model name, year, price, fuel type etc. The data-set was scraped from an old car selling section of bikroy.com. At present, used car sales are increasing day by day not only in our country but also all over the world. So, there Used Car Price Prediction system can be an important role. Besides this prediction of used car prices is crucial for both buyers and sellers in the automotive market. Because in the current situation, sellers choose prices randomly or without much consideration, leaving buyers unaware of the car’s genuine price in the present market. Additionally, sellers themselves may lack the current value of their vehicle. To address this challenge, we have constructed a highly effective model. In this system, regression algorithms are utilized because they provide continuous value as an output rather than categorical ones. This enables us to predict the actual price of a car rather than just its price range. For predicting old car prices, Lasso Regression emerged as the superior model. The R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> of 0.943 was the highest among the analysed algorithms where Lasso Regression scored.