|
Title:
|
ORDER PRODUCT CATEGORY ESTIMATION USING ACCESS LOG IN E-COMMERCE SITE |
|
Author(s):
|
Tomohiro Koketsu, Hidekazu Yanagimoto, Michifumi Yoshioka |
|
ISBN:
|
978-989-8704-04-7 |
|
Editors:
|
Philip Powell, Miguel Baptista Nunes and Pedro Isaías |
|
Year:
|
2014 |
|
Edition:
|
Single |
|
Keywords:
|
Access Log Analysis, Data mining, Recommendation System, Neighborhood user, Collaborative filtering, PageRank |
|
Type:
|
Full Paper |
|
First Page:
|
43 |
|
Last Page:
|
50 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
A lot of recommendation systems on EC sites use user's order histories in order to decide recommendation items. In general recommendation systems items are selected based on neighborhood users defined according to similarity among the order histories. However, the method cannot be applied to new users who have never purchased anything in an EC site and do not define the neighborhood users based on their order histories. The problem is called the cold start problem. In order to overcome the problem we proposed a method which uses user's access logs to make user profile instead of his/her order histories. Although the access log is less reflective of the users preference than the order history, we can estimate their intent by careful access log analysis because the access log consists of users review processes for their purchase. Therefore, to clarify users' intent we use only web pages related to decision of order products. And in order to find these web pages we analyze access log of users who ordered the same product or same category. Then we use these pages for making the user profile. In experiments we estimate neighborhood users of new users using their profiles constructed with access logs. And we predict a category of a product which new users will purchase to examine the efficiency of our proposed method. From experiments we found that there were some categories in which the proposed method can correctly predict new users target, we confirmed the effectiveness of our proposed method as a solution for cold start problem. |
|
|
|
|
|
|
