A proactive food demand forecasting-inventory management approach under weather disruptions

Effective demand forecasting has become crucial to strengthening system resilience, reducing food waste, and achieving sustainability in food systems. Despite recent advances in leveraging machine learning for food demand forecasting, most existing models remain static and assume stable demand patterns, posing a challenge for adapting to demand changes during disruption events. This paper develops a proactive approach that leverages demand forecasting outputs and weather disruption flags to guide inventory replenishment, ensuring adaptability to varying demand conditions across three weather disruption events while reducing waste. This paper first uses a stacking model to predict next-day demand for a food retailer, leveraging real-world historical and weather datasets. Additionally, three weather-disruption flags are identified from real weather data using rule-based approaches. The proposed methodology further uses predicted demand and disruption flags to inform inventory order quantities. The proposed proactive approach is assessed using real-world data from the Australian food market, and the findings reveal that the model performs consistently across the three weather disruption events, achieving an average accuracy of 86% across all conditions. Additionally, the findings highlight the effectiveness of the integrated approach in strengthening system resilience, reducing food waste, and supporting more sustainable, adaptive food-supply operations during weather disruptions.