Second-Hand Car Price Prediction

Abstract

Predicting the price of second-hand or used cars is an important as well as an interesting problem. The efforts required in achieving the desired price of the used car give a rough sketch about the amount at which the car can be sold at the best price. The challenging part is to find the best price of the used cars based upon the actual features of the car. The highest co-related features are considered and are used to build the model by using Random Forest Regression technique. The features which were used to build the model should be given as input to the system for predicting the price. Random Forest is the best technique as it is a classifier that contains a number of decision trees on various subsets of the given data set and takes the average to improve upon the predictive accuracy of that data set. This ensures that the predicted price is worthy.