A CONCEPTUAL EXPLORATION OF ARTIFICIAL INTELLIGENCE-ENABLED DEMAND FORECASTING MECHANISMS IN INDIAN SUPPLY CHAIN MANAGEMENT: A SYSTEMATIC PERSPECTIVE

Abstract

This study explores the application of Artificial Intelligence (AI) tools, combined with Natural Language Processing (NLP) techniques, to enable disruption-free supply chain management of electronic spare parts in India’s automobile sector, with a particular focus on electric vehicles (EVs). Recognizing the industry's critical role in India's economy, the research employs a comprehensive literature review and a case study methodology, including an analysis of Maruti Suzuki’s supply chain challenges. The literature review, structured into three phases, assesses AI tool suitability, evaluates the effectiveness of Artificial Neural Networks (ANNs) in demand forecasting, and investigates AI applications within the automotive sector. Findings highlight that AI-driven techniques—such as machine learning models, deep learning architectures like LSTM, and NLP-based sentiment analysis—significantly improve demand forecasting accuracy by integrating both internal and external factors, including market trends and socio-economic indicators. Despite facing challenges like data quality, infrastructure gaps, and skill shortages, the sector shows strong potential for AI adoption.