Abstract
This paper addresses recommendation diversification. Existing diversification methods have difficulty in dealing with the tradeoff between accuracy and diversity. We point out the root of the problem in diversification methods and propose a novel method that can avoid the problem. Our method aims to find an optimal solution of the objective function that is carefully designed to consider user preference and the diversity among recommended items simultaneously. In addition, we propose an item clustering and a greedy approximation to achieve efficiency in recommendation.
Original language | English |
---|---|
Pages (from-to) | 244-248 |
Number of pages | 5 |
Journal | IEICE Transactions on Information and Systems |
Volume | E101D |
Issue number | 1 |
DOIs | |
State | Published - Jan 2018 |
Bibliographical note
Publisher Copyright:Copyright © 2018 The Institute of Electronics, Information and Communication Engineers
Keywords
- Diversification
- E-commerce
- Recommender system