A Comprehensive Review of E-Commerce System for Sale Prediction Using Triple Pseudo-Siamese Network with Giant Trevally Optimizer

Abstract

The rapid expansion of e-commerce platforms has created a strong demand for accurate sales prediction systems that can analyze large volumes of transactional and behavioral data. Effective demand forecasting helps online retailers optimize inventory management, improve supply chain planning, and design efficient marketing strategies. Traditional statistical forecasting methods often struggle to capture nonlinear patterns and complex relationships within modern retail datasets. As a result, machine learning and deep learning techniques have become increasingly popular for predicting product demand in digital commerce environments. This review examines recent developments in e-commerce sales prediction models, focusing on deep learning architectures and optimization techniques. In particular, the study discusses the potential of the Triple Pseudo-Siamese Network for learning similarity patterns from multiple data streams and the Giant Trevally Optimizer (GTO) for improving model parameter optimization. By analyzing research published recently, the paper highlights current trends, compares existing forecasting approaches, and identifies future research directions for building intelligent and scalable e-commerce demand prediction systems.