Due to the numerous elements that influence the price of a used vehicle on the market, determining if the quoted price of a used car is accurate is a difficult undertaking. The goal of this project was to create machine learning models that can properly forecast the price of a used car based on its attributes to allow buyers to make educated decisions. On a dataset consisting of the sale prices of various brands and models, we have developed and evaluate several learning approaches. We examined the results of numerous machine learning algorithms, such as Linear Regression, K-NN Regression, Support Vector Regression, XGB Regression, Random Forest Regression, Extra Trees Regression, Ridge Regression, Lasso Regression, and Decision Tree Regressor, and selected the best one based on our evaluations of each algorithm. The car's pricing is determined based on several factors. Regression Algorithms are employed because they offer us with a continuous number as an output rather than a categorised value, allowing us to anticipate the specific price of a car rather than its price range. Pre-processed data is simulated into different regression techniques and each model has been evaluated to choose the best one. To know more read the paper called vehicle_price_prediction.pdf in paper folder of this project.
This project is hosted via Heroku Application. Check it out @ www.mastercar.herokuapp.com
Languages and frameworks used - Python, Flask, HTML, CSS