Abstract
Although fashion-related products account for most of the online shopping categories, it becomes more difficult for users to search and find products matching their taste and needs as the number of items available online increases explosively. Personalized recommendation of items is the best method for both reducing user effort on searching for items and expanding sales opportunity for sellers. Unfortunately, experimental studies and research on fashion item recommendation for online shopping users are lacking. In this paper, we propose a novel recommendation framework suitable for online apparel items. To overcome the rating sparsity problem of online apparel datasets, we derive implicit ratings from user log data and generate predicted ratings for item clusters by user-based collaborative filtering. The ratings are combined with a network constructed by an item click trend, which serves as a personalized recommendation through a random walk. An empirical evaluation on a large-scale real-world dataset obtained from an apparel retailer demonstrates the effectiveness of our method.
Highlights
Fashion-related products ranked the most popular of global online shopping categories, based on purchases up to November 2016 [1]
It is noted that the purchase of apparel items differs from the purchase or consumption of digital content such as movies and news in terms of item price and access patterns
According to our experimental data, the 10% truncated mean of the prices of 18,979 items is 167,529 KRW, and 70% of all users who purchased any items for one month purchased only one or two items
Summary
Fashion-related products ranked the most popular of global online shopping categories (with58% of online purchases), based on purchases up to November 2016 [1]. As the number of fashion products available online dramatically increases, users spend considerable time looking for preferred products and sometimes fail to find products of interest. This is especially prominent in fashion shopping, because the attributes of fashion products are difficult to describe or classify. A general approach for recommending fashion items is to explain each user’s taste with item attributes such as color, material, and price of items, or/and user profile information such as age and gender [2]. Several studies [6,7,8] have been performed to further classify additional features
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
