[1]张子蓬,郝世林.基于机器学习的新能源汽车残值评估方法[J].湖北工业大学学报,2019,34(5):67-71.
　ZHANG Zipeng,HAO Shilin.Research on Residual Value Evaluation Method of New Energy Vehicle Based on Machine Learning[J].,2019,34(5):67-71.
点击复制

基于机器学习的新能源汽车残值评估方法()
分享到：

《湖北工业大学学报》[ISSN:1003-4684/CN:42-1752/Z]

卷:
34卷
期数:
2019年第5期
页码:
67-71
栏目:
湖北工业大学学报
出版日期:
2019-10-30

文章信息/Info

Title:
Research on Residual Value Evaluation Method of New Energy Vehicle Based on Machine Learning
文章编号:
1003-4684(2019)05-0067-05
作者:
张子蓬;  郝世林
湖北工业大学计算机学院， 湖北  武汉 430068
Author(s):
ZHANG Zipeng;  HAO Shilin
School of Computer Science, Hubei Univ. of Tech., Wuhan 430068, China
关键词:
新能源汽车;  机器学习;  大数据;  残值评估
Keywords:
new energy vehicles;  machine learning;  big data;  residual value assessment
分类号:
TP391.4
文献标志码:
A
摘要:
针对现有汽车残值评估方法信息使用较少、严重依赖人工检测、误差大和无法解决新能源汽车残值评估的问题，基于梯度提升回归树模型，使用行驶里程、使用时间、功率、过户次数等多维特征数据，训练模型对残值进行预测。从选取惩罚项、树的深度、基学习器类型以及提取特征重要性方面优化模型。最后，使用Stacking模型集成算法对二阶多项式、XGBoost、LightGBM模型进行集成。实验结果表明，使用Stacking集成后的模型可以根据当前车况数据自动计算残值，不需要人工检测，具有实时性，较其他方法有更高的准确度。
Abstract:
Aiming at the problem of less use of information, heavy reliance on manual detection, large error and inability to solve the problem of residual value evaluation of new energy vehicles in the existing vehicle residual value assessment method, a method for estimating the residual value of new energy vehicles based on machine learning is proposed. The method, based on the gradient boosting regression tree model, uses the multidimensional feature data such as mileage, time, power, and number of transfers, and the training model to predict the residual value. The model is optimized from the selection of penalty terms, the depth of the tree, the type of base learner, and the extraction of feature importance information. Finally, the secondorder polynomial, XGBoost, and LightGBM models are integrated using a stacked model integration algorithm. The experimental results show that the model with stack integration can automatically calculate the residual value according to the current vehicle condition data, without manual detection, and has realtime performance, which has higher accuracy than other methods.

参考文献/References:

[1] 张弦.基于主题模型的车辆残值评估研究[D].南京:南京大学 , 2018.
[2] 中永(苏州)信息技术有限公司. 一种二手车检测评价分析及残值评估系统:中国，109883725[P].2019.06.14.
[3] 广东数鼎科技有限公司. 基于大数据的汽车残值预测模型及预测方法:中国，108154275[P],2017.12.29.
[4] Hu J, Min J. Automated detection of driver fatigue based on EEG signals using gradient boosting decision tree model[J]. Cognitive Neurodynamics, 2018, 12(12):1-10.
[5] Friedman J H. Greedy function approximation: A gradient boosting machine[J]. Annals of Statistics, 2000, 29(5):1189-1232.
[6] Son J. Tracking-by-segmentation with online gradient boosting decision tree[C]// IEEE International Conference on Computer Vision, 2016.
[7] Chen T, Guestrin C. XGBoost: a scalable tree boosting system[C]// Acm Sigkdd International Conference on Knowledge Discovery & Data Mining, 2016.
[8] Zhou Z H. Ensemble methods-foundations and algorithms[M]. Taylor & Francis,\[s.n.\],2012.

备注/Memo

备注/Memo:
［收稿日期］ 2019-08-09
［基金项目］ 国家自然科学基金青年基金项目（61603127）
［第一作者］ 张子蓬(1968-)， 男， 山东武城人，理学博士，湖北工业大学副教授，研究方向为嵌入式系统，人工智能
更新日期/Last Update: 2019-11-21