A device receives video data concerning a plurality of customers and a product in a plurality of physical retail locations. The device processes the video data and determines actions of the plurality of customers in relation to the product in the plurality of physical retail locations, by: determining, for a customer of the plurality of customers, an activity of the customer in relation to the product, and determining, for the customer, an eye gaze direction of the customer relative to the product. The device determines categories for the actions of the plurality of customers in relation to the product. The device generates a report that indicates one or more of the categories for the actions of the plurality of customers in relation to the product and sends the report to a client device to permit the client device to display the report.