Recommendence and Fashionsence

Abstract

The use of Artificial Intelligence (AI) techniques has become prevalent with almost all e-commerce sites. Following the trend, today's Fashion recommender systems are no exception, which widely use AI for catering to multiple use-cases. [3][4]. However this is still quite far from replicating the personalized shopping experience in a fashion store. Through this paper and demonstration we try and replicate the offline experience in an online world by using a Natural Language chatbot powered by multiple deep learning models. Athena, the personal shopping adviser in the presented system enables user interaction in natural language via a web-browser based application (extensible to a mobile application). The application is powered by two underlying machine learning components - Recommendence and Fashionsence. The recommendation system Recommendence is an ensemble of deep learning based and graph based collaborative filtering recommenders and is able to provide personalized fashion recommendations to the users. The Fashionsence component is a deep learning based model which can learn a fashion sense from online, trend and stylist data to recommend a trending fashionable set of items from the product inventory. This entire system is integrated via an orchestrating layer.