Research for Car Price Prediction Base on Machine Learning

Abstract

This report details a machine learning project aimed at predicting car prices, which is crucial and meaningful for business owners to forecast the market, avoid financial loss, and for buyers to have a rough overview of each car’s price. To accomplish the goal, this project using the Car Price Prediction Challenge dataset from Kaggle. The dataset includes a variety of automobile attributes such as brand, model, year of manufacture, engine specifications, mileage, and other relevant factors. The project's goal was to create an accurate and reliable model to predict car prices based on these characteristics. To accomplish this, the paper utilized multiple machine-learning algorithms and techniques to analyze the dataset. This research’s findings highlighted the effectiveness of these machine-learning methods in car price prediction. The random forest regressor emerged as the best-performing model, achieving high accuracy with a low mean squared error and a high R-squared value. Additionally, the feature importance analysis sheds light on the key factors influencing car prices, offering a deeper understanding of market dynamics.