Domain Adaptation for Demand Prediction in Retail
Speaker: Niloofar Tarighat聽(supervised by Maxime Cohen and James Clark)
Although many approaches have been developed to accurately predict the demand of products based on their historical sales data, demand prediction is still a complex issue especially when there is a domain shift between training and testing data. In this work, we study three examples of domain shifts in the context of retail: outbreak of the COVID-19 pandemic, opening a new store, and introducing a new product.
This talk is one of a series of three exciting presentations given by graduate students as part of their research work at the retail innovation lab, in partnership with Couche-Tard. They will be presenting an overview of their research projects, study objectives, challenges faced, results, and their real-world application in retail. Representatives of the relevant business units from Couche-Tard will also be present.
