Artificial Intelligence Techniques for E-Commerce System for Sale Prediction Using Triple Pseudo-Siamese Network with Giant Trevally Optimizer: Trends and Challenges

Abstract

The rapid growth of e-commerce platforms has generated massive volumes of digital data, creating opportunities for advanced predictive analytics systems that can forecast product demand accurately. Sales prediction is a critical component of e-commerce operations because it helps businesses optimize inventory management, improve supply chain planning, and enhance customer satisfaction. Traditional statistical forecasting techniques such as regression and ARIMA models have been widely used in retail forecasting, but they often struggle to capture nonlinear relationships and complex patterns present in large-scale e-commerce datasets. As a result, artificial intelligence and deep learning models have become increasingly important in predicting sales trends and consumer demand patterns.

This paper presents a comprehensive review of artificial intelligence techniques for e-commerce sales prediction, focusing on advanced deep learning architectures such as Triple Pseudo-Siamese Networks and optimization methods like the Giant Trevally Optimizer (GTO). The study analyzes research contributions published between 2020 and 2023, examining machine learning algorithms, neural network models, and predictive analytics techniques used for demand forecasting in digital commerce environments. The review also provides comparative analysis of existing forecasting models and highlights current challenges and future research directions in intelligent e-commerce prediction systems. AI-driven forecasting systems have been shown to significantly improve prediction accuracy and operational efficiency in online retail environments.