Used Car Price Prediction Based on Machine Learning Algorithms

DOI

10.2991/978-94-6239-801-6_140How to use a DOI?

Keywords

used car price prediction; ensemble learning; XGBoost; random forest; combined boosting

Abstract

Accurate used car price prediction has become increasingly important as the second-hand vehicle market continues to grow. Buyers and sellers often struggle to agree on fair prices because of information gaps. Expert-based pricing, while common, tends to be slow and inconsistent across different markets. Machine learning could help, but it is not obvious which algorithm works best for this particular problem. Five methods were compared here, namely Linear Regression, k-Nearest Neighbor (KNN), Random Forest, XGBoost, and a Combined Boosting model that blends Random Forest and XGBoost outputs through weighted averaging. The experiments used a Kaggle dataset of 4,009 records with 12 vehicle attributes, split 70/30 into training and test sets. Mean Squared Error served as the evaluation metric. Ensemble methods clearly beat linear and instance-based models. XGBoost gave the best results among single models, yet the Combined Boosting approach achieved the lowest test error overall. The fused model appears to capture price patterns more reliably than any individual algorithm alone.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Mingliang Wei
PY  - 2026
DA  - 2026/10/23
TI  - Used Car Price Prediction Based on Machine Learning Algorithms
BT  - Proceedings of the 2026 2nd International Conference on Financial Innovation and Marketing Management (FIMM 2026)
PB  - Atlantis Press
SP  - 1348
EP  - 1355
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6239-801-6_140
DO  - 10.2991/978-94-6239-801-6_140
ID  - Wei2026
ER  -