Abstract
Corporate fraud risk detection is a branch of fraud. It may exist in various industries and cause economic problems. Effective identification of corporate 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 artificial 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 behaviors.
Keywords
- Intelligent optimization algorithm
- self-attention mechanism
- BP neural network
- fractional-order
- fraud detection
Cite this article
@article{cai-6419,
author = {Wei Liu and MingMing Liu and Chun Yan and Man Qi and LuLu Zhang},
title = {Corporate Fraud Detection Based on Improved BP Neural Network},
journal = {Computing and Informatics},
volume = {43},
number = {3},
pages = {611--632},
year = {2024},
issn = {1335-9150},
doi = {10.31577/cai_2024_3_611}
}
TY - JOUR AU - Wei Liu AU - MingMing Liu AU - Chun Yan AU - Man Qi AU - LuLu Zhang TI - Corporate Fraud Detection Based on Improved BP Neural Network JO - Computing and Informatics VL - 43 IS - 3 SP - 611 EP - 632 PY - 2024 SN - 1335-9150 DO - 10.31577/cai_2024_3_611 UR - https://doi.org/10.31577/cai_2024_3_611 KW - Intelligent optimization algorithm KW - self-attention mechanism KW - BP neural network KW - fractional-order KW - fraud detection ER -
Liu, W., Liu, M., Yan, C., Qi, M., & Zhang, L. (2024). Corporate Fraud Detection Based on Improved BP Neural Network. Computing and Informatics, 43(3), 611–632. https://doi.org/10.31577/cai_2024_3_611