AI-Driven Demand Forecasting to Reduce Waste in FMCG Supply Chains: A Case Study of Nestlé

Abstract

The Fast-Moving Consumer Goods(FMCG) industry faces significant challenges related to waste across its supply chains, with global food waste estimated at approximately 1.3 billion tonnes each year. This project explores how artificial intelligence (AI) can significantly improve demand forecasting within FMCG supply chain, using Nestle as a primary case study. Drawing on the extensive review of academic literature, industry reports, and Nestlé’s implementation strategies, the study demonstrates that AI-driven demand forecasting systems can reduce forecasting errors up to 30%and decrease food waste by as much as 87%. The research examines several forecasting models, including Long Short-Term Memory (LSTM) networks, Autoregressive Integrated Moving Average (ARIMA), and Prophet, a forecasting algorithm developed by Facebook, to evaluate their effectiveness in predicting consumer demand patterns. The study indicates that Nestlé’s adoption of Al technologies across its supply chain has led to notable improvements in operational efficiency, cost reduction, and environmental sustainability. The study will add value to the literature on sustainable supply chain management by offering concrete evidence of the transformative power of AI in creating a solution to one of the most pressing issues in the industry. The major suggestions are to implement hybrid forecasting models, incorporating real-time information, and to create collaborative data-sharing models between the partners of the supply chains to achieve the maximum waste reduction.