Order picking is a labour-intensive activity in distribution centres, making slotting decisions critical for productivity.  Slotting is often managed reactively and without consistent metrics for performance quantification. This study presents a systematic literature review (SLR) that examines how the impact of slotting strategies on picking productivity can be quantified and how artificial intelligence (AI) can enable a transition toward proactive and dynamic slotting optimisation. Following a structured SLR, literature published between 2020 and 2026 was retrieved from Scopus, Web of Science, and IEEE Xplore, resulting in 27 eligible studies for analysis. The findings indicate that effective SKU placement consistently reduces picker travel distance and picking time while improving throughput and order fulfilment performance, with reported productivity gains exceeding 60% in some literature. The review further reveals a transition toward AI-driven slotting approaches, integrating demand forecasting, optimisation algorithms, and simulation techniques to support proactive decision-making. By consolidating quantifiable performance metrics and  AI-enabled methods, this study provides a structured approach to give real-world insights into slotting techniques and evaluations and predictive optimisation, highlighting key opportunities for possible future implementations and validation.

Keywords

Predictive slotting, SKU allocation, Order picking productivity, Artificial Intelligence, Systematic Literature Review.