Fair Price Prediction System for Used Cars in Sri Lanka Using Machine Learning and Robotic Process Automation

Abstract

The prices of most of the brand-new cars are rapidly increased by car manufacturers due to the increment of prices in raw materials and inflation rates. Also, the taxes for importing brand new cars have been rising consistently during the last decade in Sri Lanka. Due to these factors, most of the time Sri Lankan middle and lower-class people tend to buy used cars (Toyota Corolla) rather importing brand-new cars. With this increment of demand in used cars, some of the used car sellers take advantage of this scenario by listing unrealistic prices for the used cars and most of the used car buyers getting caught on this. This work focuses on creating a used car price prediction system for Sri Lanka using supervised learning techniques. For the study, Analysis with different suitable machine learning models is performed using an online data set to discover the best suitable regression models. The selected models are trained using an actual Sri Lankan used car data set which is expected to be extracted from online car advertisement websites with the help of Robotic Process Automation (RPA) technology. In the end, a web application will be presented to the users (Used car buyers) which accepts features of the car as inputs and provide a predicted fair price for the expected particular used car as the output.