Introducing Artificial Intelligence to Increase Efficiency in Warehouse Logistics: A Case Study

This paper examines how Artificial Intelligence (AI) forecasting and discrete-event simulation can support adaptive warehouse planning by integrating efficiency, workload balance, and operational resilience. Using distribution warehouse data, machine-learning models forecast daily delivery occurrence and order quantities, while simulation models represent warehouse processes, identify capacity constraints, and test staffing and layout scenarios. The results show that predictive analytics provides a stable basis for short-term planning, while simulation identifies order picking as the main operational bottleneck and the area of highest resource utilisation. The study contributes to cybernetic and systems-thinking research by operationalising an integrated planning workflow in which predictive feedback informs simulation-based experimentation and dynamic capacity alignment. The proposed framework integrates throughput, resource utilisation, workload distribution, and labour strain into a single adaptive planning approach. The paper offers a replicable analytical approach for researchers and practical guidance for managers seeking smoother workflows and more sustainable resource use.