Optimization of product category allocation in multiple warehouses to minimize splitting of online supermarket customer orders

In an online supermarket, people may purchase multiple items in a single order for convenience or to obtain free delivery. Multi-item customer orders often need to be split into multiple shipments because the ordered items may be stored in different warehouses. Order splitting results in higher shipping costs. One way to reduce splitting is to store and retrieve all the items in a single warehouse. However, due to the vast volume of items sold by online supermarkets, it is difficult to build and operate such a warehouse. Another way is to optimize the allocation of products in multiple warehouses to reduce order splitting. In this paper, we propose a K-links heuristic clustering algorithm to optimize the product category allocation among multiple warehouses based on the distribution of multi-item orders to minimize the total number of order splits. Using online order and inventory data from a large Chinese online supermarket, we demonstrate that our algorithm performs well and dramatically reduces order splitting.