Research on a Financial Fraud Identification Model by Fusing a Convolutional Neural Network

Abstract

To address the problems of low accuracy, poor real-time performance, and a single model of current financial fraud identification methods for listed companies, this paper proposes a financial fraud identification model based on a convolutional neural network (CNN) and support vector machine (SVM). This paper selects non-financial A-share listed companies punished by the China Securities Regulatory Commission and its local branches, the Ministry of Finance, the Shenzhen Stock Exchange, and the Shanghai Stock Exchange from 2007- to 2022 for financial fraud as training samples. After data collation and oversampling, the samples of financial fraud are rebalanced. The features of the financial fraud samples of listed companies are extracted via a convolutional neural network (CNN), and the extracted features are input into a support vector machine (SVM) to classify the data. On this basis, a financial fraud identification method based on a convolutional neural network and support vector machine (SVM) fusion prediction model (CNN-SVM) is established. After statistical testing, the experimental results indicate that the proposed method accurately identifies financial fraud and outperforms existing detection methods in all aspects.

Keywords

Financial fraud identification;Convolutional neural network;Support vector machine;Machine learning

Figures