Article: Cross-border e-commerce credit risk early warning model based on deep learning Journal: International Journal of Reasoning-based Intelligent Systems (IJRIS) 2025 Vol.17 No.10 pp.1 - 9 Abstract: Credit risk challenges in cross-border e-commerce are becoming more pronounced, significantly hindering the sector's healthy progression. Existing early warning mechanisms cannot effectively analyse the complex, nonlinear patterns and dynamic changes in cross-border e-commerce transactions, causing low detection accuracy. To this end, this study first introduces an enhanced SMOTE algorithm to address class imbalance in credit hazard data, followed by the selection and standardisation of key hazard indicators. Then one-dimensional CNN is used to deeply mine the features of impact indicators. The particle swarm optimisation (PSO) algorithm is utilised to fine-tune the parameters of the extreme learning machine (ELM), with the optimised ELM subsequently generating the risk warning classifications. The experimental outcome indicates that the forecasting accuracy of the offered model is improved by at least 4.05%, demonstrating significant gains in warning system accuracy. Inderscience Publishers - linking academia, business and industry through research

Title: Cross-border e-commerce credit risk early warning model based on deep learning

Authors: Yanping Jiang; Peng Du

Addresses: Department of Digital Commerce, Yantai Engineering and Technology College, Yantai 264000, China ' Department of Digital Commerce, Yantai Engineering and Technology College, Yantai 264000, China

Abstract: Credit risk challenges in cross-border e-commerce are becoming more pronounced, significantly hindering the sector's healthy progression. Existing early warning mechanisms cannot effectively analyse the complex, nonlinear patterns and dynamic changes in cross-border e-commerce transactions, causing low detection accuracy. To this end, this study first introduces an enhanced SMOTE algorithm to address class imbalance in credit hazard data, followed by the selection and standardisation of key hazard indicators. Then one-dimensional CNN is used to deeply mine the features of impact indicators. The particle swarm optimisation (PSO) algorithm is utilised to fine-tune the parameters of the extreme learning machine (ELM), with the optimised ELM subsequently generating the risk warning classifications. The experimental outcome indicates that the forecasting accuracy of the offered model is improved by at least 4.05%, demonstrating significant gains in warning system accuracy.

Keywords: credit risk early warning; deep learning; convolutional neural network; CNN; extreme learning machine; ELM; particle swarm optimisation algorithm; PSO.

DOI: 10.1504/IJRIS.2025.148174

International Journal of Reasoning-based Intelligent Systems, 2025 Vol.17 No.10, pp.1 - 9

Received: 14 Jun 2025
Accepted: 14 Jul 2025
Published online: 27 Aug 2025 *

Title: Cross-border e-commerce credit risk early warning model based on deep learning

Keep up-to-date