Financial Crisis Prediction Based on Long-Term and Short-Term Memory Neural Network

• Published in: Wireless communications and mobile computing Vol. 2022; pp. 1 - 8
• Main Authors: Ling, Tang, Cai, Yinying
• Format: Journal Article
• Language: English
• Published: Oxford Hindawi 29.05.2022; Hindawi Limited
• Subjects: Accuracy; Algorithms; Big Data; Data analysis; Decision analysis; Decision making; Decision trees; Deep learning; Economic crisis; Feature selection; Financial analysis; Financial management; Forecasting; Goodness of fit; Machine learning; Neural networks; Optimization; Parameters; Time series
• DOI: 10.1155/2022/5728470
• ISSN: 1530-8669

Enterprise financial crisis prediction analysis can predict the business process of enterprises, so that enterprises can take corresponding strategies in time. The financial crisis prediction of listed companies can effectively reflect the business situation, so as to give investors reasonable investment advice. In order to supervise the sustainable management ability of enterprises efficiently and accurately, this paper proposed a financial crisis prediction method based on long-term and short-term memory neural network, so as to provide valuable information for decision-makers. Firstly, the data in the enterprise financial system is analyzed and extracted, and the original data is cleaned and dimensionalized by normalization and feature selection. Then, the long-term and short-term memory neural network is used to build the financial early warning model, and the wolf pack algorithm is used to optimize the initial weight and bias parameters, so as to improve the efficiency of parameter optimization. Finally, the financial data of 20 large- and medium-sized enterprises from 2019 to 2021 are verified and analyzed. The experimental results show that compared with other common machine learning methods, the constructed wolf pack-optimized long-term and short-term memory neural network has the highest prediction performance in terms of root mean square error and goodness of fit, with the goodness of fit reaching 94.2%.