Ensemble learning algorithm - research analysis on the management of financial fraud and violation in listed companies

Weihong Li; Xiujuan Xu

doi:10.31181/dmame622023785

Authors

Weihong Li Jiangxi University of Engineering, Xinyu, Jiangxi 338000, China https://orcid.org/0009-0004-7154-9663
Xiujuan Xu Jiangxi University of Engineering, Xinyu, Jiangxi 338000, China https://orcid.org/0009-0003-0287-7308

DOI:

https://doi.org/10.31181/dmame622023785

Keywords:

Ensemble algorithm, listed companies, financial fraud and violation, XGBoost

Abstract

In recent years, despite the strict "zero tolerance" crackdown on the financial fraud and violation behavior of listed companies, the cases of financial fraud, revenue and profit overstatement, and suspected fraud have continued to be exposed. This study first established a financial fraud index system and used the XGBoost algorithm to construct a prediction model for financial fraud and violations of listed companies. The indicators were selected and input into the model. A dataset was obtained for experiments. The XGBoost algorithm was compared with two other algorithms. The receiver operator characteristic (ROC) curves showed that the XGBoost algorithm had the best prediction performance among the three algorithms. It was found that the precision of the XGBoost algorithm was 93.17%, the recall rate was 92.23%, the value was 0.9270, and the area under the curve was 0.90, indicating a better performance than the prediction models based on the Gradient Boosted Decision Tree (GBDT) algorithm and the Logistics algorithm. Considering the data of various evaluation indicators, it is found that the predictive effect of the financial fraud and violation prediction model built by the XGBoost algorithm is the best.

Downloads

Download data is not yet available.

References

Adnovaldi, Y., & Wibowo, W. (2019). Analisis determinan fraud diamond terhadap deteksi fraudulent financial statement. Jurnal Informasi Perpajakan, Akuntansi dan Keuangan Publik, 14(2), 125-146. https://doi.org/10.25105/jipak.v14i2.5195

An, X., Hu, C., Liu, G., & Lin, H. (2021). Distributed online gradient boosting on data stream over multi-agent networks. Signal Processing: The Official Publication of the European Association for Signal Processing (EURASIP), 189(4), 108253. https://doi.org/10.1016/j.sigpro.2021.108253

Ardhiansyah, A. S., Kusuma, H., & Sa'Dani, O. S. (2019). Analisa pengaruh kinerja keuangan dan corporate governance terhadap kemungkinan terjadinya financial statement fraud. Jurnal REKSA: Rekayasa Keuangan, Syariah, dan Audit, 6(2), 149-165. https://doi.org/10.12928/j.reksa.v6i1.1375

Aslan, L. (2021). Financial statement fraud in the turkish financial services sector. Istanbul Business Research, 50(2), 385-409. https://doi.org/10.26650/ibr.2021.50.844527

Bai, M., Zheng, Y., & Shen, Y. (2022). Gradient boosting survival tree with applications in credit scoring. Journal of the Operational Research Society, 73(1), 39-55. https://doi.org/10.1080/01605682.2021.1919035

Chen, L., Xiu, B., & Ding, Z. (2020). Finding misstatement accounts in financial statements through ontology reasoning. IEEE Access, 1-14. https://doi.org/10.1109/ACCESS.2020.3014620

Irawan, P. A., Susilowati, D., & Puspasari, N. (2019). Detection analysis on fraudulent financial reporting using fraud score model. SAR (Soedirman Accounting Review): Journal of Accounting and Business, 4(2), 161-180. https://doi.org/10.20884/1.sar.2019.4.2.2467

Li, S. L. (2020). Data mining of corporate financial fraud based on neural network model. Computer Optics, 44(4), 665-670. DOI: 10.18287/2412-6179-CO-656

Liu, X. (2021). Empirical analysis of financial statement fraud of listed companies based on logistic regression and random forest algorithm. Journal of Mathematics, 2021(2), 1-9. https://doi.org/10.1155/2021/9241338

Sari, N. S., Sofyan, A., & Fastaqlaili, N. (2019). Analysis of fraud diamond dimension in detecting financial statement fraud. Jurnal Akuntansi Trisakti, 5(2), 171-182. https://doi.org/10.25105/jat.v5i2.4861

Sihombing, T., & Cahyadi, C. C. (2021). The effect of fraud diamond on fraudulent financial statement in asia pacific companies. Jurnal ULTIMA Accounting, 13(1), 143-155. https://doi.org/10.31937/akuntansi.v13i1.2031

Triyanto, D. N. (2019). Fraudulence financial statements analysis using pentagon fraud approach. Journal of Accounting Auditing and Business, 2(2), 26. https://doi.org/10.24198/jaab.v2i2.22641

Udhayakumar, K., Rakkiyappan, R., Li, X., & Cao, J. (2021). Mutiple psi-type stability of fractional-order quaternion-valued neural networks. Applied Mathematics and Computation, 401, 126092. https://doi.org/10.1016/j.amc.2021.126092

Westland, J. C. (2020). Predicting credit card fraud with Sarbanes-Oxley assessments and Fama-French risk factors. Intelligent Systems in Accounting, Finance & Management, 27(2), 95-107. https://doi.org/10.1002/isaf.1472

Wu, H., Chang, Y., Li, J., & Zhu, X. (2022). Financial fraud risk analysis based on audit information knowledge graph. Procedia Computer Science, 199, 780-787. https://doi.org/10.1016/j.procs.2022.01.097

Zhang, Z., Qiu, J. X., & Dai, W. (2019). A new improved boosting for imbalanced data classification. IOP Conference Series: Materials Science and Engineering, 533, 012047. https://doi.org/10.1088/1757-899X/533/1/012047

Zúiga, E., & Jesús, J. (2020). Aplicación de algoritmos Random Forest y XGBoost en una base de solicitudes de tarjetas de crédito. Ingeniería Investigación y Tecnología, 21(3), 1-16. https://doi.org/10.22201/FI.25940732E.2020.21.3.022