Research Article
Research on Financial Fraud Identification Based on Machine Learning Algorithm
@INPROCEEDINGS{10.4108/eai.9-12-2022.2327705, author={Yihan Wang and Tianyu Zhang and Yue Xie and Shiyu Cui}, title={Research on Financial Fraud Identification Based on Machine Learning Algorithm}, proceedings={Proceedings of the 4th Management Science Informatization and Economic Innovation Development Conference, MSIEID 2022, December 9-11, 2022, Chongqing, China}, publisher={EAI}, proceedings_a={MSIEID}, year={2023}, month={3}, keywords={financial falsification; machine learning; financial indicators; importance selection}, doi={10.4108/eai.9-12-2022.2327705} }- Yihan Wang
Tianyu Zhang
Yue Xie
Shiyu Cui
Year: 2023
Research on Financial Fraud Identification Based on Machine Learning Algorithm
MSIEID
EAI
DOI: 10.4108/eai.9-12-2022.2327705
Abstract
In recent years, many cases of financial fraud have occurred at home and abroad. The repeated cases of financial fraud not only bring serious property losses to investors, but also seriously affect the credit mechanism of the capital market and slow down the process of healthy development of market economy, so how to efficiently and accurately identify enterprises with financial fraud is a hot topic of academic research. In this paper, a comprehensive identification model is formed by using decision trees in machine learning algorithms as well as artificial neural networks for model construction training. The results show that the accuracy of the two algorithmic models improves after importance selection, with 74.2% and 90%, respectively. It is finally concluded that the importance selection is beneficial to improve the accuracy of the financial fraud identification model, and the artificial neural network can demonstrate better identification results in the algorithm selection.
