Recent Advances in E-commerce enterprises financial risk prediction based on hierarchical auto-associative polynomial convolutional neural network model: A Systematic Review

Abstract

The rapid expansion of e-commerce has introduced significant complexity in financial risk assessment, requiring advanced predictive models capable of handling nonlinear, high-dimensional, and dynamic data. Traditional statistical and rule-based approaches are often inadequate for capturing the diverse risk factors present in modern digital marketplaces. This systematic review explores the application of hierarchical auto-associative polynomial convolutional neural networks (CNNs) for financial risk prediction in e-commerce environments. The proposed framework integrates hierarchical feature extraction with autoencoder-based representation learning, enabling effective modeling of both micro-level transactional anomalies and macro-level systemic risks. The incorporation of polynomial convolutional operations enhances the model’s ability to capture complex nonlinear interactions within financial data, while convolutional layers exploit spatiotemporal correlations in transaction patterns. This architecture supports a wide range of applications, including credit risk assessment, fraud detection, bankruptcy prediction, and supply chain risk analysis. Empirical studies across benchmark datasets demonstrate superior performance compared to traditional machine learning models and standard deep learning approaches, particularly in terms of classification accuracy and robustness. Despite these advancements, challenges such as model interpretability, computational scalability, and handling of imbalanced datasets remain.This review provides a comprehensive overview of current methodologies and highlights future directions for developing scalable, efficient, and intelligent financial risk management systems in e-commerce.