Artificial Intelligence In Retail Demand Forecasting: Effects On Inventory Performance And Customer Satisfaction

The rapid growth of omnichannel retailing and volatile consumer demand has exposed the limitations of traditional demand forecasting techniques. Recent advances in artificial intelligence (AI) and machine learning (ML) offer superior capabilities for handling large-scale, nonlinear, and real-time retail data. This study examines the effectiveness of AI-driven demand forecasting models and their impact on inventory performance and customer satisfaction in retail environments. Drawing on prior research, the study integrates explainable AI, human–AI collaboration, managerial trust, organizational readiness, and technical debt into a comprehensive empirical framework. Using a quantitative, cross-sectional research design, data were collected from 260 retail and supply chain professionals and analyzed using regression, mediation, and moderation techniques. The findings indicate that AI-based forecasting significantly improves forecasting accuracy, reduces stockouts and excess inventory, and enhances customer satisfaction. Explainable AI and human–AI collaboration emerged as critical drivers of managerial trust and inventory decision quality, while organizational readiness strengthened and technical debt weakened AI performance outcomes. The study contributes to AI and retail analytics literature by moving beyond accuracy-focused evaluations and highlighting the strategic role of trust, explainability, and organizational context in AI adoption.