Predicting Used Car Price Based on Machine Learning
Jiayi Lin
2024
Abstract
With used car sales in many countries surpassing new car sales, the automobile industry is important to the global economy and in an unshakable position. Accurately predicting used car prices is beneficial for making wise decisions for different interested parties, including consumers, car sellers, and some financial institutions. This paper compares different regression models including Linear Regression (LR), Ridge Regression (RR), and Random Forest (RF) to determine the most reliable method for predicting used car prices. The dataset is sourced from CarDekho and has been preprocessed, which includes handling missing values, feature engineering, and anomaly detection. The RF outperforms other models in terms of performance, indicating higher prediction accuracy. However, limitations such as small sample size and potential overfitting indicate the need for further model tuning and data expansion. To increase prediction accuracy and model robustness, future research should concentrate on enhancing data quality, investigating new characteristics, and implementing sophisticated encoding techniques.
DownloadPaper Citation
in Harvard Style
Lin J. (2024). Predicting Used Car Price Based on Machine Learning. In Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI; ISBN 978-989-758-726-9, SciTePress, pages 553-560. DOI: 10.5220/0013270500004568
in Bibtex Style
@conference{ecai24,
author={Jiayi Lin},
title={Predicting Used Car Price Based on Machine Learning},
booktitle={Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI},
year={2024},
pages={553-560},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013270500004568},
isbn={978-989-758-726-9},
}
in EndNote Style
TY - CONF
JO - Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI
TI - Predicting Used Car Price Based on Machine Learning
SN - 978-989-758-726-9
AU - Lin J.
PY - 2024
SP - 553
EP - 560
DO - 10.5220/0013270500004568
PB - SciTePress