SYSTEMATIC LITERATURE REVIEW ON ARTIFICIAL INTELLIGENCE APPLICATIONS IN SUPPLY CHAIN DEMAND FORECASTING

Abstract

This systematic review investigates the applications of artificial intelligence (AI) in supply chain demand forecasting, focusing on the performance of AI-driven models compared to traditional forecasting techniques. Using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, a comprehensive search was conducted, yielding a final selection of 65 peer-reviewed articles for in-depth analysis. The review explores the advantages of AI models, particularly machine learning (ML) and deep learning (DL), in improving forecasting accuracy, scalability, and responsiveness to real-time data. It also examines AI’s applications across various industries, including retail, manufacturing, e-commerce, and logistics, where AI-driven models have significantly enhanced inventory management, production scheduling, and operational efficiency. However, the review highlights challenges related to data quality, model complexity, and high implementation costs, which limit the broader adoption of AI in demand forecasting. This study provides valuable insights into the current state of AI applications in supply chain management and suggests areas for future research, particularly in improving data management and developing more interpretable AI models to facilitate wider implementation.