Financial Fraud Data Analysis Based on Genetic Neural Networks
DOI:
https://doi.org/10.54097/qymea846Keywords:
Significance test, GA-BP neural network, Financial dataAbstract
It is used the Guotai An violation database to select 75 listed companies that were punished for financial fraud from 2011 to 2020 as fraud samples, and uses Beasley's matching principle to select 75 non fraud companies that match the fraudulent companies as matching samples. Among the 21 preliminary indicators, SPSS was used for significance testing, and factor analysis was used to reduce the significance indicators. Finally, 5 variables were selected as input variables for the data mining model, while fraud (marked as 2 for fraud and 1 for non fraud) was used as the output variable for identifying financial fraud. Using a GA-BP neural network algorithm to train and model the training group sample data, the accuracy rate reached 87.16%.
Downloads
References
[1] Cheng, X. J. (2018). Research on Financial Fraud Identification of Chinese Listed Companies Based on Data Mining [Master’s thesis]. Chongqing University of Technology. [In Chinese]
[2] Zhong, S. Q. (2021). Research on Data Preprocessing Framework Based on Machine Learning [Master’s thesis]. Xi'an University of Technology. [In Chinese]
[3] Huang, C. (2021). Research and Implementation of Anomaly Detection System Based on Time Series Data Mining [Master’s thesis]. Zhejiang University. [In Chinese]
[4] Li, Q., & Ren, C. Y. (2016). Research on the construction and early warning of accounting fraud risk index for listed companies. Journal of Xi'an Jiaotong University (Social Sciences Edition), (01), 36–43. [In Chinese]
[5] Chen, G. X., Lv, Z. J., & He, F. (2007). Empirical study on the identification of financial reporting fraud: Based on empirical data of Chinese listed companies. Audit Research, 03, 88–93. [In Chinese]
[6] Dechow, P. M., Ge, W., Larson, C. R., et al. (2011). Predicting material accounting misstatements. Contemporary Accounting Research, 28(1), 17–82.
[7] Yuan, C. S., & Han, H. L. (2008). The mechanism and empirical test of the influence of board size on financial fraud. Business Economics and Management, (03), 44–49. [In Chinese]
[8] Zhang, J. J. (2021). Research on the Identification Model of Financial Reporting Fraud in Listed Companies Based on Data Mining [Master’s thesis]. Zhejiang University. [In Chinese]
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Computer Science and Artificial Intelligence
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
