Research on corporate financial performance prediction based on self‐organizing and convolutional neural networks

Abstract

Economic risks faced by manufacturing enterprises are gradually increasing and risk reduction whilst maintaining high financial performance has become key to their survival and development of enterprises. Enterprise performance affects not only enterprise development but also does the interests of investors and creditors. Therefore, a well‐performing model for financial performance prediction is particularly important. In this paper, we combine unsupervised and supervised learning, fusing self‐organizing mapping neural networks and convolutional neural networks, and apply deep learning to financial analysis to construct a new financial performance prediction model, called SNN‐CNN. This paper uses crawler technology to obtain financial data of listed manufacturing enterprises and classifies their financial performance into five levels. It finds that enterprises with high financial performance tend to have balanced financial indicators, strong corporate vitality and stable development of various capabilities, while enterprises with low financial performance have poor repayment and profitability, significant risks in corporate operation and limited growth and development. Compared with traditional risk prediction models, the SOM‐CNN model has a higher accuracy rate, up to 95.69%.

Leveraging quantum‐inspired chimp optimization and deep neural networks for enhanced profit forecasting in financial accounting systems

“…The anticipation of profits holds significant importance in financial accounting, serving as a critical indicator for assessing a company's efficiency and enabling assessments of its financial state against its rivals (Hao, Jiali, et al, 2023). Accurately predicting profits empowers organizations to make well‐informed decisions on allocating resources, investment strategies, and future planning (Zhou et al, 2022).…”

Interpretable deep learning based text regression for financial prediction

“…Previous financial forecasting works were mainly based on numerical analysis methods on historical data, including risk prediction Qi et al (2014), return prediction Baker et al (2006); Li et al (2013), default prediction Chen and Wu (2014); Duffie et al (2007), stock price prediction Avramov and Chordia (2006); Grinblatt and Moskowitz (2004); Paye (2012), and so forth. Recently, techniques such as machine learning Ghosh et al (2018); Kamruzzaman et al (2022); Song et al (2010), deep learning Alaminos et al (2022); Kim and Ahn (2012); Zhou et al (2022) and graph neural networks Wu et al (2022); Xia et al (2022) have been applied in financial forecasting. Only focusing on historical numerical data may have certain limitations.…”

A Hybrid Approach for Predicting Corporate Financial Risk: Integrating SMOTE-ENN and NGBoost

“…With the proliferation of deep learning techniques, researchers have embarked on applying this methodology to finance-related studies [28]. Luo's research [29] conducted a rigorous comparison of Deep Learning methods, specifically DBN, with traditional models like LR, Multilayer Perceptron, and SVM.…”