Title: Risk assessment method of e-commerce transaction based on fuzzy support vector machine

Authors: Zheng Xu; Hengzhi Nie

Addresses: Department of Economics and Trade, Henan Polytechnic Institute, Nanyang, 473001, Hennan, China; Department of Business Administrator, Zhongnan University of Economics and Law, Wuhan, 430073, China ' The Academy of Digital China (FuJian), Fuzhou, 350003, China

Abstract: To improve the recall and accuracy of the evaluation index data and reduce the calculation error rate of the evaluation index, a fuzzy support vector machine based e-commerce transaction risk evaluation method is proposed. Build the evaluation index system, and cluster the evaluation index data using the nearest neighbour propagation clustering algorithm. The CRITIC algorithm is improved by using discrimination vector and conflict vector, and the index weight calculation result is obtained by using the improved CRITIC algorithm. The risk assessment model is built by combining the index weight calculation results and fuzzy support vector machine to obtain the assessment results. The experimental results show that the average recall rate of the index data of this method is 96.8%, the calculation error rate of the evaluation index is small, and the maximum accuracy rate is 99%, which shows that the practical application effect of this method is good.

Keywords: fuzzy support vector machine; electronic commerce; transaction risk assessment; nearest neighbour propagation clustering algorithm; CRITIC algorithm.

DOI: 10.1504/IJISD.2025.149106

International Journal of Innovation and Sustainable Development, 2025 Vol.19 No.5/6, pp.647 - 663

Received: 17 Jan 2023
Accepted: 21 Apr 2023
Published online: 14 Oct 2025 *

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