Predicting Accounting Fraud in Publicly Traded Chinese Firms via A PCA-RF Method

DOI

10.2991/978-94-6463-108-1_82How to use a DOI?

Keywords

fraud prediction; machine learning; Principal component analysis; random forest; combined model

Abstract

Financial fraud occurs from time to time and gradually becomes a worldwide problem with the expansion of the international capital markets and the rise of the information industry economy under the Internet eco-system. This paper provides a methodology for predicting financial fraud using basic financial data. The methodology is based on PCA-RF. Different from traditional methods such as logistic regression and support vector machine, we creatively proposed a PCA-RF model, first using principal component analysis to reduce the dimensionality of the data, then using grid search to optimize the random forest model, and finally directly selecting the raw financial data from the financial statements for direct analysis. We compare the analysis results with random forest and neural network methods, and the study finds that the PCA-RF model is superior for predicting domestic financial fraud in China. In this paper, we use an ensemble learning approach to introduce the PCA-RF method into the field of prediction of financial fraud for listed companies.

Copyright

© 2022 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Donger Chen
PY  - 2022
DA  - 2022/12/30
TI  - Predicting Accounting Fraud in Publicly Traded Chinese Firms via A PCA-RF Method
BT  - Proceedings of the 2022 International Conference on Computer Science, Information Engineering and Digital Economy (CSIEDE 2022)
PB  - Atlantis Press
SP  - 739
EP  - 748
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-108-1_82
DO  - 10.2991/978-94-6463-108-1_82
ID  - Chen2022
ER  -