Basket data-driven approach for omnichannel demand forecasting

Basket data-driven approach for omnichannel demand forecastingInternational audienceOmnichannel retailing has changed the purchasing behavior of customers in recent years, especially in online shopping, which has led to higher complexity in supply chain demand forecasting. Nowadays customers buy a variety of products in baskets that do not share similar characteristics and across various channels. In this article, we propose a new approach to forecasting demand, driven by data on customers shopping baskets. Drawing on network graph theory and market basket analysis, we identify three attributes for a product to promote the connection with other products sold together in a basket: degree, strength, and support. These attributes are used as predictor variables with an autoregressive integrated moving average model. We conduct an empirical investigation using sales and basket data related to an assortment of 24,000 products of a major cosmetics retailer in France selling through online and physical retail channels. We provide empirical evidence that using the shopping basket data improves the forecasting accuracy in omnichannel retailing. We also show that there is a considerable benefit from a joint forecasting of the online and store channels and a shared inventory between both channels