Content Based Apparel Recommendation Engine

Mudasir Ahmad Hurrah , Dr Monika Mehra, Ravinder Pal Singh

With the rapid rising of living standard, people gradually developed higher shopping enthusiasm and increasing demand for garment. Nowadays, an increasing number of people pursue fashion. However, facing too many types of garment, consumers need to try them on repeatedly, which is somewhat time and energy-consuming. Besides, it is difficult for merchants to master the real- time demand of consumers. Proposed recommendation engine utilizes tops_fashion dataset which consists nearly 183k products acquired through Amazon API interface and processes this dataset using multiple techniques like Bag_of_Words (BoW), tf, idf, Word2Vec model,VGG16 (CNN) etc to recommend similar items to a given query item. Product Advertising API acts as a gateway to Amazon's databases so that we can take advantage of Amazon's sophisticated e-commerce data and functionality. In this project, we are using Python language for coding. The proposed system can recommend product based on various features of the product such as title, color, brand, price, image but we have only used title and image features of the products. Collaborative Filtering technique suffers from cold start problem- a situation where a recommender does not have adequate information about a user or an item in order to make relevant predictions. This is one of the major problems that reduce the performance of recommendation system.