Application of Used Car Price Predictor in Indonesia Along with Machine Learning Model Comparison and SMOTE

In current times, transportation is crucial. Transportation assists us in our activities. Hence, the people are interested at alternatives such as used cars. In a transaction, product knowledge is important, yet used one for cars is uncommon. After the lift of distancing rule, interest in transport rose. Our purpose is to find how useful a predictor will be in Indonesia for providing the public of knowledge in secondhand car prices. The algorithm aims to help users to market used cars at the right price, preventing fraud. During the study, SMOTE is used to cover for the lack of sample of the dataset. The methods, Linear Regression, Random Forest, and Support Vector Machine to predict the price of used cars and compare its results based on the RMSE, MSE, MAE, <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$R^{2}$</tex> Score. To add, we have chosen an ensemble learning method, XGBoost. With the usage of the above methods, results in the price of the cars not being a simple outcome with set variables being applied with each transaction.