Deep learning: an study on financial crisis forewarning in small and medium-sized listed enterprises

Abstract

Early warning of financial crisis will greatly promote the stable development of small and medium-sized listed enterprises (listed SMEs). In this article, 13 warning indicators were selected for financial crisis prediction from five aspects: profit level, debt service level, business level, cash level, and development level. Then, the parameters of the long short-term memory (LSTM) neural network model were optimised by the whale optimisation algorithm (WOA), resulting in the WOA-LSTM model. The WOA-LSTM model achieved an accuracy of 0.975 in predicting financial crises for listed SMEs. The performance of the WOA-LSTM model was significantly enhanced when using the filtered 13 indicators as inputs, compared to using the original 24 indicators. The findings prove the dependability of the WOA-LSTM model in warning financial crises of listed SMEs and the feasibility of its application in practice.