Corporate Financial Fraud Identification and Crisis Forewarning Based on The Partial Least Squares Method

Authors

  • Yuying Li North China University of Science and Technology, Tangshan, Hebei 063210, China

Abstract

Conducting research into financial fraud and predicting financial crises is an important research issue. In this paper, we describe the development of a model based on partial least squares (PLS) combined with a support vector machine (SVM). Components were extracted through PLS and were used as the input of SVM. Then, data were distinguished using SVM. An analysis was carried out on the collected samples. The results show that after component extraction by PLS, the model achieved an average accuracy of 83.61% for fraud identification, and the model also achieved good performance in relation to financial crisis forewarning, with an accuracy of 95%, 90.51% and 88.45% for Year T-1, T-2 and T-3, respectively. The results verify the reliability of the method and that the method can be applied in practice.

Keywords: partial least squares, financial fraud identification, financial crisis warning, support vector machine

Cite As

Y. Li, "Corporate Financial Fraud Identification and Crisis Forewarning Based on The Partial Least Squares Method",
Engineering Intelligent Systems, vol. 30 no. 3, pp. 211-216, 2022.



Downloads

Published

2022-05-01

Issue

Vol. 30 No. 3 (2022): International Journal of Engineering Intelligent Systems

Section

General Submission

License

The submission of a paper implies that, if accepted for publication, it will not be published elsewhere in the same form, in any language, without the prior consent of the publisher. Before publication, authors are requested to assign copyright to CRL Publishing Ltd. This allows CRL to sanction photocopying, and to authorize the reprinting of issues or volumes according to demand. Authors' traditional rights will not be jeopardized by assigning Copyright in this way, as they retain the right to reuse the material following publication, and to veto third-party publication.