中小微企业的信贷决策研究

Research on Credit Decision of Micro,Small and Medium-sized Enterprises

建立了MGA-SVM算法的信誉等级评价模型,对无信贷记录的中小微企业进行信誉等级评价,风险等级分为“无风险”“轻微风险”“一般风险”“较大风险”“大风险”;从利润率、有效交易率、净利润增长率等方面建立基于AHP-模糊数学方法的信贷风险评价模型、PLS方法的贷款利率最优决策模型量化企业的信贷风险,为银行提供具体的信贷策略;进行模型检验,得到核函数类型预测的正确率最高,均达到90%以上。

This paper establishes the reputation rating evaluation model of MGA-SVM algorithm to evaluate the reputation of micro,small and medium-sized enterprises without credit record.The risk ratings are divided into no risk,minor risk,general risk,larger risk and big risk.From profit rate,effective transaction rate,net profit growth rate and other aspects,it establishes credit risk evaluation model of AHP-fuzzy mathematics method and optimal decision model of loan interest rate of PLS method to quantify the credit risk of enterprises and provide banks with specific credit strategies.Finally,the model test is carried out,and the prediction accuracy of the kernel function type is the highest,reaching more than 90%.