Title: A risk identification method for abnormal accounting data based on weighted random forest

Authors: Yan Shi

Addresses: School of Accounting, Xi'an Eurasia University, Xi'an, 710065, China

Abstract: In order to improve the identification accuracy, accuracy and time-consuming of traditional financial risk identification methods, this paper proposes a risk identification method for financial abnormal data based on weighted random forest. Firstly, SMOTE algorithm is used to collect abnormal financial data; secondly, the original accounting data is decomposed into features, and the features of abnormal data are extracted through random forests; then, the index weight is calculated according to the entropy weight method; finally, the negative gradient fitting is used to determine the loss function, and the weighted random forest method is used to solve the loss function value, and the recognition result is obtained. The results show that the identification accuracy of this method can reach 99.9%, the accuracy rate can reach 96.06%, and the time consumption is only 6.8 seconds, indicating that the risk identification effect of this method is good.

Keywords: SMOTE algorithm; weighted random forest; loss function; negative gradient fitting.

DOI: 10.1504/IJITM.2024.139575

International Journal of Information Technology and Management, 2024 Vol.23 No.3/4, pp.304 - 317

Received: 29 Dec 2022
Accepted: 27 Feb 2023
Published online: 04 Jul 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article