Used car price prediction based on XGBoost and retention rate

doi:10.19682/j.cnki.1005-8885.2024.1002

中国邮电高校学报(英文) ›› 2024, Vol. 31 ›› Issue (3): 72-79.doi: 10.19682/j.cnki.1005-8885.2024.1002

• Artificial Intelligence • 上一篇下一篇

Used car price prediction based on XGBoost and retention rate

沈雨田¹,陈建¹,戴敏¹,张思瑞²,徐晶¹,王青³

1. College of Mechanical Engineering, Yangzhou University, Yangzhou 225127, China
2. College of Economics and Management, Southeast University Chengxian College, Nanjing 210088, China
3. Shandong Shuncheng Automobile Trade Co. , Ltd, Jinan 250000, China

收稿日期:2022-06-12 修回日期:2022-11-10 出版日期:2024-06-30 发布日期:2024-06-30
通讯作者: 陈建 E-mail:chenjian.tud@hotmail.com
基金资助:
the Postgraduate Education Reform Project of Yangzhou University (JGLX2021_002).

Used car price prediction based on XGBoost and retention rate

Shen Yutian, Chen Jian, Dai Min, Zhang Sirui, Xu Jing, Wang Qing

1. College of Mechanical Engineering, Yangzhou University, Yangzhou 225127, China
2. College of Economics and Management, Southeast University Chengxian College, Nanjing 210088, China
3. Shandong Shuncheng Automobile Trade Co. , Ltd, Jinan 250000, China

Received:2022-06-12 Revised:2022-11-10 Online:2024-06-30 Published:2024-06-30
Contact: Jian CHEN E-mail:chenjian.tud@hotmail.com
Supported by:
the Postgraduate Education Reform Project of Yangzhou University (JGLX2021_002).

摘要/Abstract

摘要： In order to improve the accuracy of used car price prediction, a machine learning prediction model based on the
retention rate is proposed in this paper. Firstly, a random forest algorithm is used to filter the variables in the data.
Seven main characteristic variables that affect used car prices, such as new car price, service time, mileage and so
on, are filtered out. Then, the linear regression classification method is introduced to classify the test data into high
and low retention rate data. After that, the extreme gradient boosting ( XGBoost) regression model is built for the
two datasets respectively. The prediction results show that the comprehensive evaluation index of the proposed
model is 0. 548, which is significantly improved compared to 0. 488 of the original XGBoost model. Finally,
compared with other representative machine learning algorithms, this model shows certain advantages in terms of
mean absolute percentage error (MAPE), 5% accuracy rate and comprehensive evaluation index. As a result, the
retention rate-based machine learning model established in this paper has significant advantages in terms of the
accuracy of used car price prediction.

关键词: random forest, data dimensionality reduction, extreme gradient boosting (XGBoost), retention rate, price prediction

Abstract: In order to improve the accuracy of used car price prediction, a machine learning prediction model based on the
retention rate is proposed in this paper. Firstly, a random forest algorithm is used to filter the variables in the data.
Seven main characteristic variables that affect used car prices, such as new car price, service time, mileage and so
on, are filtered out. Then, the linear regression classification method is introduced to classify the test data into high
and low retention rate data. After that, the extreme gradient boosting ( XGBoost) regression model is built for the
two datasets respectively. The prediction results show that the comprehensive evaluation index of the proposed
model is 0. 548, which is significantly improved compared to 0. 488 of the original XGBoost model. Finally,
compared with other representative machine learning algorithms, this model shows certain advantages in terms of
mean absolute percentage error (MAPE), 5% accuracy rate and comprehensive evaluation index. As a result, the
retention rate-based machine learning model established in this paper has significant advantages in terms of the
accuracy of used car price prediction.

Key words: random forest, data dimensionality reduction, extreme gradient boosting (XGBoost), retention rate, price prediction

Shen Yutian, Chen Jian, Dai Min, Zhang Sirui, Xu Jing, Wang Qing. Used car price prediction based on XGBoost and retention rate[J]. The Journal of China Universities of Posts and Telecommunications, 2024, 31(3): 72-79.

参考文献

1. XIA Z B, YANG J C, ZHANG J Z. Domestic used car market bucks the trend of red Tesla price inversion demand exceeds supply. China Business Journal, 2022-02-19 (33). (in Chinese)

2. REDDY A, KAMALRAJ R, LISTIANI M, et al. Old/Used cars price prediction using machine learning algorithms. IITM Journal of Management and IT, 2021, 12(1): 32-35.

3. PUROHIT D. Exploring the relationship between the markets for new and used durable goods: the case of automobiles. Marketing Science, 1992, 11(2): 154-167.

4. ANDREWS T, BENZING C. The determinants of price in internet auctions of used cars. Atlantic Economic Journal, 2007, 35(1): 43-57.

5. ENGERS M, HARTMANN M, STEM S. Annual miles drive used car prices. Journal of Applied Eeconometrics, 2009, 24(1): 1-33.

6. RICHARDSON M S. Determinants of used car resale value. Bachelor's Thesis. Springs, CO, USA: The Colorado College, 2009.

7. SHEN G Q, WANG Y S, ZHU Q. New model for residual value prediction of the used car based on BP neural network and nonlinear curve fit. Proceedings of the 3rd International Conference on Measuring Technology and Mechatronics Automation (MTMA’11), 2011, Jan 6-7, Shanghai, China. Piscataway, NJ, USA: IEEE, 2011: 682-685.

8. XIE Y, WEN H, ZHANG J. Used car price evaluation method based on machine learning. Enterprise Technology Development, 2015, 34(11): 116-118. (in Chinese)

9. KE G l, MENG Q, FINLEY T, et al. LightGBM: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems 30: Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS'17), 2017, Dec 4-9, Long Beach, CA, USA. Red Hook, NY, USA: Curran Associates, 2017: 3146-3154.

10. CHEN Y F, LI C L, XU M L. Business analytics for used car price prediction with statistical models. Proceedings of the 3rd International Conference on Economic Management and Cultural Industry (ICEMCI’21), 2021, Oct 22-24, Guangzhou, China. Amsterdam, Netherlands: Atlantis Press, 2021: 542-547.

11. WIESŁAW P, MAKSYMILIAN K. A constructive induction of feature using random forest approach. Procedia Computer Science, 2020, 176: 3318-3323.

12. ZHONG J C, SUN Y S, PENG W, et al. XGBFEMF: An XGBoost-based framework for essential protein prediction. IEEE Transactions on NanoBioscience, 2018, 17(3): 243-250.

13. JOKI K, BAGIROV A M, KARMITSA N, et al. Cluster wise support vector linear regression. European Journal of Operational Research, 2020, 287(1): 19-35.

14. LI X L, MA L F, CHEN P, et al. Probabilistic solar irradiance forecasting based on XGBoost. Energy Reports, 2022, 8(S5): 1087-1095.

15. CHICCO D, WARRENS M J, JURMAN G. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Computer Science, 2021, 7: Article e623.

Used car price prediction based on XGBoost and retention rate

Used car price prediction based on XGBoost and retention rate

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价