当前位置: X-MOL 学术IEEJ Trans. Electr. Electron. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Bayesian Network Oriented Transfer Learning Method for Credit Scoring Model
IEEJ Transactions on Electrical and Electronic Engineering ( IF 1.0 ) Pub Date : 2021-06-29 , DOI: 10.1002/tee.23417
Koichi Iwai 1 , Masanori Akiyoshi 2 , Tomoki Hamagami 1
Affiliation  

Credit scoring model (CSM) is a risk management tool that assesses the credit worthiness of a customer borrower by estimating her probability of default based on historical data. Traditionally CSM is built by logit model or decision tree algorithm in financial companies, and in recent studies CSM has been integrated with machine learning algorithms such as random forest and gradient boosting to process a number of complex attributes of customer borrowers. On the other hand, CSM has been facing a critical challenge - the domain adaptation of customer borrowers. For domain adaptation problem, transfer learning techniques are generally utilized, however, it is quite difficult to execute precise predictions for unknown domain datasets in CSM because the distributions of labels could be different depending on the characteristics of domains. Therefore, there is no appropriate transfer learning method to solve domain adaptation problem in credit scoring. In this paper we propose a comprehensive transfer learning framework using Bayesian network to extract useful knowledge based on probability distributions to predict probability of default of customer borrowers more precisely than existing machine learning and transfer learning methods. Experimental results showed the proposed method performed over the existing machine learning and transfer learning methods for accuracy of predictions. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

中文翻译:

面向信用评分模型的贝叶斯网络迁移学习方法

信用评分模型 (CSM) 是一种风险管理工具,它通过根据历史数据估计客户借款人的违约概率来评估其信用价值。传统上,CSM 是由金融公司的 logit 模型或决策树算法构建的,而在最近的研究中,CSM 已与机器学习算法(如随机森林和梯度提升)相结合,以处理客户借款人的许多复杂属性。另一方面,CSM 一直面临着一个严峻的挑战——客户借款人的域适应。对于域适应问题,通常使用迁移学习技术,但是在 CSM 中对未知域数据集执行精确预测非常困难,因为标签的分布可能会根据域的特征而有所不同。所以,没有合适的迁移学习方法来解决信用评分中的领域适应问题。在本文中,我们提出了一个综合的迁移学习框架,使用贝叶斯网络提取基于概率分布的有用知识,比现有的机器学习和迁移学习方法更准确地预测客户借款人的违约概率。实验结果表明,所提出的方法优于现有的机器学习和迁移学习方法,以提高预测的准确性。© 2021 日本电气工程师学会。由 Wiley Periodicals LLC 出版。在本文中,我们提出了一个综合的迁移学习框架,使用贝叶斯网络提取基于概率分布的有用知识,比现有的机器学习和迁移学习方法更准确地预测客户借款人的违约概率。实验结果表明,所提出的方法优于现有的机器学习和迁移学习方法,以提高预测的准确性。© 2021 日本电气工程师学会。由 Wiley Periodicals LLC 出版。在本文中,我们提出了一个综合的迁移学习框架,使用贝叶斯网络提取基于概率分布的有用知识,比现有的机器学习和迁移学习方法更准确地预测客户借款人的违约概率。实验结果表明,所提出的方法优于现有的机器学习和迁移学习方法,以提高预测的准确性。© 2021 日本电气工程师学会。由 Wiley Periodicals LLC 出版。© 2021 日本电气工程师学会。由 Wiley Periodicals LLC 出版。© 2021 日本电气工程师学会。由 Wiley Periodicals LLC 出版。
更新日期:2021-08-13
down
wechat
bug