基于代价敏感XGBoost的企业信用评估模型

Enterprise credit evaluation model based on cost sensitive XGBoost

我国信用不良的企业数量远小于信用良好的企业数量,样本类别的极端不平衡导致传统的信用评估模型在训练时无法充分学习信用不良企业的特征.为提高极端梯度提升算法(Extreme Gradient Boosting,XGBoost)在企业信用评估这种不平衡分类问题中的准确率,提出一种基于代价敏感XGBoost的企业信用评估模型.在XGBoost算法拟合过程中,加入代价敏感损失函数迫使模型更加关注少数类的特征,并引入贝叶斯优化调整模型的重要超参数.以我国A股市场中小板块企业2016—2020年数据为样本,实证结果表明,基于代价敏感XGBoost的企业信用评估模型能够在保证总体识别精度的情况下提高对信用不良企业的识别准确率.

In China,the number of enterprises with bad credit is much smaller than that of enterprises with good credit.The extreme imbalance of sample categories results in the traditional credit evaluation model unable to fully learn the characteristics of bad credit enterprises during training.In order to improve the accuracy of extreme gradient boosting(XGBoost)in unbalanced classification problems such as enterprise credit evaluation,an enterprise credit evaluation model based on cost sensitive XGBoost was proposed.In the process of XGBoost algorithm fitting,the cost sensitive loss function was added to force the model to pay more attention to the characteristics of minority classes,and the bayesian optimization was introduced to adjust the hyperparameters of the model.Taking the datas of small and medium-sized enterprises in China's A-share market from 2016 to 2020 as the sample,the experimental results show that the enterprise credit evaluation model based on cost sensitive XGBoost can improve the identification accuracy of bad credit enterprises while ensuring the overall identification accuracy.