基于最优指标组合的代价敏感违约预测模型——以A股中小企业为例

A Cost-Sensitive Default Prediction Model Based on Optimal Combination of Indicators:A Case Study of A-Share SMEs

企业违约预测是在当下时刻推断企业未来时刻发生违约事件的概率,与经济和社会息息相关。本研究的贡献在于:一是构造了兼顾指标组合违约预测精度和指标个数的多目标函数,通过sigmoid函数将蜉蝣算法转化为二进制蜉蝣算法,将其引入金融风险领域进行最优指标组合的遴选。二是在逻辑回归模型的对数似然函数中,给违约企业添加一个惩罚系数,以违约预测精度F-measure最大,反推最优的惩罚系数值,在保证总体判别精度的前提下,提高模型对违约企业的识别精度;同时使得逻辑回归求解的目标函数更贴合实际情况,确保了估计的权重向量更准确地反映指标数据与其违约状态间的函数关系。中小企业的实证研究表明:“高管年薪披露方式”“前十大股东是否存在关联”和“监事会持股比例”等企业内部非财务因素,以及“人均地区生产总值”“中长期贷款基准利率”和“货币和准货币供应量同比增长率”等宏观经济因素对中小企业违约预测的影响不容忽视。该方法可以提升对企业信用风险的识别能力,降低商业银行的不良贷款率。

Corporate default prediction is to infer the default probability in the future,which is related to the economy and society.The contribution of this paper is three folds.First,it constructs a multiobjective function that considers the performance of default prediction and the number of indicators.It transforms the mayfly algorithm into a binary mayfly algorithm using a sigmoid function,which is introduced into the financial risk field to select the optimal indicator combination.Then,in the loglikelihood function of the logistic regression,it adds a penalty coefficient to defaulted enterprises to maximize the F-measure and compute the optimal penalty coefficient to improve the accuracy of defaulted enterprises under the premise of ensuring the overall discriminatory accuracy.It makes the objective function of the logistic regression more closely match the actual situation and ensures that the estimated weight vector more accurately reflects the functional relationship between the indicator data and its default status.It is found that internal non-financial factors such as“executive salary disclosure”,“whether the top ten shareholders are related”and“supervisory board shareholding”and the macroeconomic factors such as“per capita GDP”,“benchmark interest rate for medium and long-term loans”and“money and quasi-money supply growth rate”have a key influence on default prediction of small and medium-sized enterprises(SMEs).The proposed methodology can improve the identification of corporate credit risk and reduce the non-performing loan rate of commercial banks.