Credit Risk Assessment

This study utilizes the annual loan ledger data obtained from a commercial bank located in Jiangsu Province, China, which is called ChinaZJB. The ChinaZJB dataset consists of 1,329 valid samples of SMEs after merging the non-financial behavioral information and soft information on credit rating with the financial information, loan information, and non-financial basic information found in the annual loan ledger data. Among them, 108 SMEs have default records, while 1,221 SMEs have no default records, resulting in an imbalanced ratio of approximately 1:11.To check the robustness of the proposed model, five datasets from the UC Irvine (UCI) machine-learning repository, that is, the Polish 1, Polish 2, Polish 3, Australian, and Taiwan credit datasets, were used for robustness checks in this study.

本研究采用取自中国江苏省某商业银行的年度贷款台账数据，该数据集命名为ChinaZJB。ChinaZJB数据集通过将信用评级相关的非财务行为信息与软信息，与年度贷款台账数据中涵盖的财务信息、贷款信息及非财务基础信息进行融合，最终得到1329条中小微企业（Small and Medium Enterprises, SMEs）有效样本。其中，108家中小微企业存在违约记录，1221家无违约记录，样本失衡比例约为1:11。为验证所提模型的稳健性，本研究选用加州大学欧文分校（UC Irvine, UCI）机器学习数据集库中的5个数据集开展稳健性检验，具体包括波兰1（Polish 1）、波兰2（Polish 2）、波兰3（Polish 3）、澳大利亚信用数据集以及中国台湾信用数据集。

搜集汇总

背景与挑战

背景概述

该数据集名为'Credit Risk Assessment'，基于中国江苏一家商业银行的年度贷款台账数据，包含1,329个有效中小企业样本，整合了财务信息、贷款信息和非金融信息等多维度数据。数据集中违约与非违约样本比例约为1:11，呈现出明显的类别不平衡特点，适用于信用风险评估和违约预测研究。