Optimization of Cross-Border E-Commerce Financial Regulatory Risk Model Relying on Edge Computing

This paper constructs a cross-border e-commerce supply chain network based on convolutional neural networks (CNNs) to identify risk factors between enterprise nodes and divide cross-border e-commerce risks into three levels, and important impact indicators of financial risks for cross-border enterprises were analyzed, verifying the model's effectiveness. This paper combines edge computing and CNN models to optimize the model. Taking J Company's as an example, the risk factors of J Company's are tested. The results demonstrate that integrating edge computing with the CNN model can significantly lower the operating costs for J Company's by approximately 35% without compromising model accuracy. Additionally, edge computing effectively reduces system cache usage, decreases system overhead and delay, and enhances feedback speed. The research in this paper proves that the characteristics of edge computing can also play an important role in the cross-border e-commerce financial risk supervision model, which can provide a reference for cross-border e-commerce enterprises to optimize.