One-to-one recommendation system in apparel online shopping

Abstract

We propose an apparel online shopping site with a fashion adviser existing on the Internet. The fashion adviser, who has detailed knowledge about the fashions in the real shop, selects and coordinates the clothes of the customer's preference. Because customers without a detailed knowledge of fashion were not able to choose clothes suitable for their preferences from among the large selection on conventional apparel shopping sites, we created a system that analyzes the customer's preferences by the AHP technique, forms a cluster by correlation of clothes, and analyzes the market basket. As a result, this system can coordinate clothes appropriate to the taste of an individual customer. It can also make recommendations of other clothes based on past sales data. © 2010 Wiley Periodicals, Inc.