Online shopping has become an important part of retail operations. This is a development that has been ongoing for some time, but has definitely picked up speed because of the COVID-19 pandemic. Many traditional ’brick-and-mortar’ stores opened online sales channels, leveraging their physical store to fulfil online customer demand through curb-side pick-up or home delivery.
This tight integration of online and offline sales channels is called omni-channel retailing, and its growth has resulted in new challenges for retailers, especially with regards to the management of their inventories. One of these challenges is the allocation of available store inventory to the online and offline channel. In other words, the retailer should decide how to divide its inventory across the channels, even though the products are present at the same location. Practically, this rationing of inventory relates to storing part of the inventory in the backroom to satisfy online demand. This way, they don’t run the risk of selling something online that is in reality not available anymore in the store. However, it might also mean that you are holding products back that you could have sold to a customer in the store. Figuring out how much of the inventory to hold back is therefore not easy!
In a new study, we focus on exactly this decision problem for a brick-and-mortar store that uses the inventory to fulfil both in-store demand and online orders. To analyse this decision process, we model the rationing and ordering decisions as a Markov Decision Problem that maximises the expected profit. This enables us to identify the optimal strategies for both the number of products to stock and how to allocate them to the two sales channels. Based on the structure of these optimal strategies, we are also able to determine easy-to-use decision rules that can help make near-optimal decisions and that scale well to retailers with many products. It is also worth noting that these decision rules turn out to combine elements from several well-known inventory management rules for ordering and rationing, further facilitating implementations in practice.
For more information, the full paper can be found online at:
Joost Goedhart, René Haijema, Renzo Akkerman (2022), Inventory rationing and replenishment for an omni-channel retailer. Computers & Operations Research, Volume 140, 105647, https://doi.org/10.1016/j.cor.2021.105647.