Demand forecasting in micro-fulfillment centers using association rule-based machine learning

The rise of Micro-Fulfillment Centers (MFCs) has heightened the need for accurate and interpretable demand forecasting. To address the volatile nature of MFC demand, we propose Association Rule-based Machine Learning (ARML), which integrates association rule mining with machine learning to achieve feature selection and predictive accuracy. This study performs statistical validation and systematic evaluation of ARML across multiple experimental settings that reflect varying degrees of demand volatility and operational complexity. Using parcel delivery data from South Korea, we identify the key conditions under which ARML performs effectively, demonstrating its robustness and practical relevance for real-world MFC operations. Furthermore, by leveraging association rules as a mechanism for interpretability, ARML contributes to the field of eXplainable Artificial Intelligence (XAI). The results confirm that ARML consistently outperforms benchmark models, offering a scalable, interpretable, and high-performing solution for dynamic e-commerce logistics.