ARTIFICIAL INTELLIGENCE AND DIGITAL TRANSFORMATION IN COMMERCE: APPLICATIONS IN DEMAND FORECASTING AND INVENTORY MANAGEMENT

Abstract

Artificial intelligence (AI) is becoming an important component of digital transformation in commerce, particularly in activities that depend on the timely interpretation of large and changing datasets. Among these, demand forecasting and inventory management directly influence purchasing, warehousing, distribution and customer service. This paper examines how AI-supported forecasting can connect historical sales, customer behaviour, prices, promotions, seasonal effects and selected external factors with inventory decisions. Using a narrative review of concepts and applications supported by selected peer-reviewed literature on AI and supply chain management, it discusses machine learning, deep learning, time-series analysis and predictive analytics as tools for identifying demand patterns and supporting replenishment decisions. The review indicates that AI can strengthen planning by processing multiple variables at speed, identifying relationships that are difficult to detect manually and supporting more responsive inventory decisions, but it does not remove the need for managerial judgement. Forecast quality depends on the quality and relevance of data, and implementation can be constrained by cost, cybersecurity requirements, skills gaps, system integration and unexpected changes in customer behaviour. The paper therefore presents AI-enabled demand forecasting as a decision-support capability rather than a fully autonomous replacement for commercial management and proposes an implementation framework in which data preparation, forecasting, inventory planning, monitoring and continuous improvement are connected stages. It concludes that the value of AI in commerce depends not only on the forecasting technique selected but also on the quality of business processes, human oversight and responsible data management.