Optimisation of warehouse for second-hand items using Machine Learning

Abstract: Warehouse management and organisation often use the popularity of items to assign placements in the warehouse and predict sales. However, when dealing with only unique second-hand items another solution is needed. This master's thesis therefore aims to identify influential features for customers buying items together and use this information to optimise Sellpy's warehouse management. Through data analyses, three features were identified as most influential: brand, demography, and type. These features were used to create a K-Means clustering model to group items in the warehouse, and the resulting model was evaluated against a demography baseline and random. Additionally, a second K-Means model was trained using the selected features and the age of items to differentiate between fast-moving and slow-moving items. The results of the analyses showed that the demography baseline performed the best when picking only one order at a time, while the K-Means models performed equally well when picking multiple orders simultaneously. Furthermore, organising items in the warehouse based on the K-Means clustering algorithm could significantly improve efficiency by reducing walking distances for warehouse workers compared to the random approach used today. In conclusion, this thesis highlights the importance of data analysis and clustering in optimising warehouse management for Sellpy. The identified influential features and K-Means clustering models provide a solid foundation for enhancing Sellpy's warehouse management.