Apparel Recommendation System using Content-Based Filtering

Abstract

Nowadays, people are constantly moving towards various fashion products as a result the e-commerce market for garments is growing rapidly. Online stores must update their features according to user requirements and preferences. However, there are too many options for users to select from these online stores which may leave them in a dilemma to identify the correct outfit, save the user time, and increase sales, efficient recommendation systems are becoming a necessity for online retailers. In this paper, we proposed an Apparel Recommendation System that generates recommendations for users based on their input. We used a real-world data set taken from the online market giant Amazon using Amazon’s Product Advertising API. We aim to use keywords like brand, color, size, etc., to recommend. Data exploration to get detailed information about our dataset, Data Cleaning(pre-processing) to remove invalid sections, Model selection (We have compared different feature extraction techniques like bag of words, TF-IDF, and word2vec model) to find out efficient techniques and Deployment of the model that could facilitate recommendation system to simplify the task of apparel recommendation system. The accuracy of the model is identified using the response time and content matching.