Converting items into vectors to determine optimized locations

Abstract

Generating a vector space model to analyze menu items for restaurants in order to determine optimized geographic locations for merchants to position restaurants is described herein. In one example, the techniques include converting the menu items into vectors using the vector space model, and using the vectors, grouping or assigning the menu items to cuisine types. Once assigned to cuisine types, one or more servers of a food-ordering service may analyze transaction histories for customers in a particular geographic area to determine how 'adventurous' the customers are, or how diverse the customer's orders are amongst cuisine types. If the customers in a particular geographic area are adventurous or diverse consumers, the food-ordering service may recommend that a merchant establish a dine-in restaurant in the geographic area, offer food delivery to the geographic area, and/or include the geographic area in a schedule for a mobile restaurant.