A Hybrid Collaborative Filtering Model Using Customer Search Keyword Data for Product Recommendation

A recommender system is a system that recommends products or services that best meet the preferences of each customer using statistical or machine learning techniques. Collaborative Filtering (CF) has been used the most as an algorithm for implementing recommender systems. However, in most cases, it has only used purchase history or customer's ratings though there are numerous available data provided by customers. E-commerce customers frequently use a search function to find the products they are interested in among the vast array of products offered. Such search keywords data may be a very useful information source for modeling customer's preference. However, it is rarely used as a source of information for recommendation systems. In this paper, we propose a novel hybrid CF model based on Doc2Vec using search keywords and purchase history data of online shopping mall customers. To validate the applicability of the proposed model, we empirically tested its performance using a real-world online shopping mall data in Korea. As a result, we found that search keywords data might effectively represent the preference of customers, and contribute to the improvement of conventional CF.