Credit Decision System for Micro, Small and Medium Enterprises (MSMEs) Based on Neural Network Algorithm and Nonlinear Programming

Abstract

Micro, Small and Medium Enterprises (MSMEs) play an important role in economic development However, due to the prevalence of information asymmetry, MSMEs are hard to borrow money and banks have difficulties in accurately assessing credit risks of MSMEs. In order to solve these problems in credit decision, we establish a credit risk assessment model for MSMEs based on the principle of back propagation (BP) neural network learning algorithm. After iteratively solve the nonlinear programming problem with the interior point method, a credit decision model is obtained. As the production and operation of enterprises and economic benefits may be affected by some unexpected factors, following that, the credit strategy is adjusted according to the enterprise's own business condition and market influencing factors.