Complementary Fashion Recommendation using Compatible Modelling

Abstract

The last two years of COVID-19, repeated lockdowns, and plain fear of stepping out of the house have fast-paced the adoption of eCommerce by many decades. Total online spending in May 2020 hit $82.1 billion (about $210 per person in the US), up 77% year-over-year. Even though it is good news for retailers as they do not need to invest in numerous brick-and-mortar stores, they face the conundrum of serving an invisible customer. They cannot see the customer, do not have any insight into customer preferences, and might have a limited transaction history for the customers as well as the product sales. Walking into a store, salespeople see the customer and can recommend clothes based on the customer's looks. Our motivation is to create a cold start recommendation engine that does not need any knowledge of user preferences, user history, item propensity, or any other data to recommend products to the customer. In this paper we are trying to solve two problems, given a product, what are the similar products and what are the complementary products that will complete the outfit.