One to One Recommendation System for Apparel Online Shopping

摘要

Clients who visit an apparel marketing website but have little previous knowledge of fashions tend to have difficulties selecting clothes that suit their tastes. Faced with an immense number of products on display, they can become quite confused and even hesitate to make any selections at all. This study proposes a system that supports online purchases of garments with functions to select and recommend garments on the basis of the customer's tastes. The system has three basic capabilities: (1) It analyzes the customer's tastes using the analytical hierarchy process (AHP) and selects and suggests clothes. (2) It designates a priority for suggesting the garments using correlations found by clustering. (3) It suggests second purchases of items that have been chosen by previous customers with similar tastes who bought a garment that the current online customer has just decided to buy. The second purchases are selected using market basket analysis. Two databases are essential to this process: one for the attributes of garments and one for simultaneous purchases of garments.