Enterprise Financial Risk Early Warning Using BP Neural Network Under Internet of Things and Rough Set Theory

Abstract

In this paper, an enterprise financial risk indicator system is established to warn about the financial risk of enterprises. First, the related knowledge of financial risk and its measurement is introduced. Next, the financial risk indicator system of small- and medium-sized enterprises (SMEs) is established based on back propagation neural network (BPNN). The rough set theory is adopted to simplify the indicator. Finally, the BPNN model is used to predict the financial situation of SMEs. The results show that in the 490th iteration, the performance of the BPNN-based financial risk early warning system for SMEs can reach the optimal and meet the accuracy requirements of initialization. The error of the enterprise financial risk early warning model converges to the target error, so the calculation result is credible. The actual output after training is close to the expected output. By judging the actual output value, it can be known that the financial risk status of SMEs in 2016, 2017 and 2018 is of low alarm. This exploration has a certain preventive effect on the financial risk of enterprises and provides a basis for the rapid development of enterprises.