Corporate fraud detection based on improved BP neural network

Corporate fraud risk detection is a branch of fraud. It may exist in various industries and cause economic problems. Effective identification of cor porate fraud can protect the safety of funds for investors in some sense. This paper proposes a classifier model of a fractional-order immune BP neural network based on the self-attention mechanism to improve efficiency. The improved artifi cial immune algorithm with dynamic region contraction strategy is used to optimize the initialization process of the BP neural network. Furthermore, it combines the self-attention mechanism to design the input layer. Finally, Caputo fractional non causal calculus is used to optimize the parameter updating process in BP neural network. The experiment results indicate that our model has fast convergence rate and powerful capacity of detection, and performs efficiently in detecting fraud behaviours.

[1] Wang, A.—Ma, B.—Hu, H.: The Progress of Research on Corporate Fraud. Economic Perspectives, Vol. 48, 2019, No. 2, pp. 115–132 (in Chinese).
[2] Liu, B.—He, Y.: Application of Artificial Intelligence Algorithm in the Field of AntiFraud under Epidemic Situation. China Financial Computer, Vol. 27, 2020, No. 4,
pp. 55–57 (in Chinese).
[3] Forough, J.—Momtazi, S.: Sequential Credit Card Fraud Detection: A Joint
Deep Neural Network and Probabilistic Graphical Model Approach. Expert Systems,
Vol. 39, 2022, No. 1, Art. No. e12795, doi: 10.1111/exsy.12795.
[4] Zhang, J.—Vukotic, I.—Gardner, R.: Anomaly Detection in Wide Area Network Mesh Using Two Machine Learning Anomaly Detection Algorithms. CoRR,
2018, doi: 10.48550/arXiv.1801.10094.
[5] Alharbi, A.—Alshammari, M.—Okon, O. D.—Alabrah, A.—Rauf, H. T.—
Alyami, H.—Meraj, T.: A Novel text2IMG Mechanism of Credit Card Fraud
Detection: A Deep Learning Approach. Electronics, Vol. 11, 2022, No. 5, Art. No. 756,
doi: 10.3390/electronics11050756.
[6] Yan, C.—Zhang, X.: Life Insurance Customer Churn Prediction Algorithm Based
on Improved K-Means and BP-Adaboost. Journal of Shandong University of Scien-
Corporate Fraud Detection Based on Improved BP Neural Network 629
Ce and Technology: Natural Science Edition, Vol. 41, 2022, No. 1, pp. 54–65, doi:
10.16452/j.cnki.sdkjzk.2022.01.006 (in Chinese).
[7] Cheng, P.—Chen, D.—Wang, J.: Clustering of the Body Shape of the Adult Male
by Using Principal Component Analysis and Genetic Algorithm–BP Neural Network.
Soft Computing, Vol. 24, 2020, No. 17, pp. 13219–13237, doi: 10.1007/s00500-020-
04735-9.
[8] Yang, C.: Research on Health Insurance Fraud Identification Based on BP Neural
Network. Ph.D. Thesis. Qingdao University, 2014.
[9] Yan, C.—Li, M.—Zhou, X.: Improved Genetic Algorithm for Vehicle Insurance
Fraud Identification Model Based on BP Neural Network. Journal of Shandong University of Science and Technology: Natural Science Edition, Vol. 38, 2019, No. 5,
pp. 72–80, doi: 10.16452/j.cnki.sdkjzk.2019.05.009 (in Chinese).
[10] Hu, Z.: Research on Auto Insurance Fraud Identification Based on Neural Network. Master Thesis. Guizhou University of Finance and Economics, 2021, doi:
10.27731/d.cnki.ggzcj.2021.000425 (in Chinese).
[11] Ma, X.—Li, X.—Song, Y.—Zheng, X.—Zhang, Z.—He, R.: A BP Neural Network for Identifying Corporate Financial Fraud. 2019 IEEE International
Conference on Intelligence and Security Informatics (ISI), 2019, pp. 191–193, doi:
10.1109/ISI.2019.8823408.
[12] Mohamed, A.—Bandi, A. F. M.—Tamrin, A. R.—Jaafar, M. D.—
Hasan, S.—Jusof, F.: Telecommunication Fraud Prediction Using Backpropagation Neural Network. 2009 International Conference of Soft Computing and
Pattern Recognition, 2009, pp. 259–265, doi: 10.1109/SoCPaR.2009.60.
[13] Xu, X.—Arshad, M. A.—Ali, U.—Mahmood, A.: The GM-BP Neural Network
Prediction Model for International Competitiveness of Computer Information Service
Industry. Algorithms, Vol. 14, 2021, No. 11, Art. No. 308, doi: 10.3390/a14110308.
[14] Adamo, J. M.—Anguita, D.: Object Oriented Design of a Simulator for Large
BP Neural Networks. In: Mira, J., Sandoval, F. (Eds.): From Natural to Artificial
Neural Computation (IWANN 1995). Springer, Berlin, Heidelberg, Lecture Notes in
Computer Science, Vol. 930, 1995, pp. 642–649, doi: 10.1007/3-540-59497-3 233.
[15] Liu, T.—Jiang, T.—Li, A. et al.: Remote Sensing Estimation of Forest Stock Volume Based on Neural Network and Different Site Quality. Journal of Shandong University of Science and Technology (Natural Science), Vol. 38, 2019, No. 2, pp. 25–35.
[16] Zhang, M.—Liu, D.—Wang, Q.—Zhao, B.—Bai, O.—Sun, J.: Detection
of Alertness-Related EEG Signals Based on Decision Fused BP Neural Network.
Biomedical Signal Processing and Control, Vol. 74, 2022, Art. No. 103479, doi:
10.1016/j.bspc.2022.103479.
[17] Zhang, D.—Yang, G.—Zhao, X.—Yang, X.—Kaohsiung, F.: Optimization
Design of Vane Diffuser and Volute in Vertical Centrifugal Pump Based on Back
Propagation Neural Network. Journal of Agricultural Machinery, Vol. 53, 2022, No. 4,
pp. 130–139 (in Chinese).
[18] Dong, C.—Dong, L.—Yang, M.: The Application of the BP Neural Network
in the Nonlinear Optimization. In: Cao, B., Wang, G., Guo, S., Chen, S. (Eds.):
Fuzzy Information and Engineering 2010. Springer, Berlin, Heidelberg, Advances in
630 W. Liu, M. Liu, C. Yan, M. Qi, L. Zhang
Intelligent and Soft Computing, Vol. 78, 2010, pp. 727–732, doi: 10.1007/978-3-642-
14880-4 80.
[19] Jia, W.—Zhao, D.—Shen, T.—Ding, S.—Zhao, Y.—Hu, C.: An Optimized
Classification Algorithm by BP Neural Network Based on PLS and HCA. Applied
Intelligence, Vol. 43, 2015, No. 1, pp. 176–191, doi: 10.1007/s10489-014-0618-x.
[20] Maru, A.—Dutta, A.—Kumar, K. V.—Mohapatra, D. P.: Software Fault Localization Using BP Neural Network Based on Function and Branch Coverage. Evolutionary Intelligence, Vol. 14, 2021, No. 1, pp. 87–104, doi: 10.1007/s12065-019-00318-
2.
[21] Zhao, Y.: Research and Application on BP Neural Network Algorithm. 2015
International Industrial Informatics and Computer Engineering Conference, 2015,
pp. 1444–1447, doi: 10.2991/iiicec-15.2015.321.
[22] Zhang, X.—Tan, J.—Han, J.: Fault Diagnosis Method Based on BP Neural Network. Ph.D. Thesis. 2002 (in Chinese).
[23] Bahdanau, D.—Cho, K.—Bengio, Y.: Neural Machine Translation by Jointly
Learning to Align and Translate. CoRR, 2014, doi: 10.48550/arXiv.1409.0473.
[24] Tian, Y.—Liang, Y. Q.—Peng, Y. J.: Cuckoo Search Algorithm Based on
Stochastic Gradient Descent. In: Kr¨omer, P., Zhang, H., Liang, Y., Pan, J. S. (Eds.):
Proceedings of the Fifth Euro-China Conference on Intelligent Data Analysis and Applications (ECC 2018). Springer, Cham, Advances in Intelligent Systems and Computing, Vol. 891, 2019, pp. 90–99, doi: 10.1007/978-3-030-03766-6 10.
[25] Huang, J.—Wang, J.: Fractional-Order Non-Causal BP Neural Networks Model.
Journal of Computer Engineering and Applications, Vol. 57, 2021, No. 23, pp. 91–97
(in Chinese).
[26] Li, Y.: Research and Application of Improved Algorithm of Classifier Based on BP
Neural Network. Master Thesis. China University of Geosciences, Beijing, 2019, doi:
10.27493/d.cnki.gzdzy.2019.001390 (in Chinese).
[27] Ye, X.—Yao, P.—Long, F.—Zhuang, Z.: Iris Image Real-Time Pre-Estimation
Using Compound BP Neural Network. In: Zhang, D., Jain, A. K. (Eds.): Advances
in Biometrics (ICB 2006). Springer, Berlin, Heidelberg, Lecture Notes in Computer
Science, Vol. 3832, 2005, pp. 450–456, doi: 10.1007/11608288 60.
[28] Hooda, N.—Bawa, S.—Rana, P. S.: Fraudulent Firm Classification: A Case
Study of an External Audit. Applied Artificial Intelligence, Vol. 32, 2018, No. 1,
pp. 48–64, doi: 10.1080/08839514.2018.1451032.
[29] Xiong, H.: Research and Implementation of Sensitive Text Classification Algorithm
Based on Artificial Immune System. Master Thesis. Xi’an University of Electronic
Science and Technology, 2021, doi: 10.27389/d.cnki.gxadu.2021.003047 (in Chinese).
[30] Wang, R.—Xu, H.—Li, B.—Feng, Y.: Research on Method of Determining Hidden Layer Nodes in BP Neural Network. Computer Technology and Development,
Vol. 28, 2018, No. 4, pp. 31–35 (in