Abstract
Recommender systems make use of different sources of information for providing users with recommendations of items. Such systems are often based on either collaborative filtering methods which make automatic predictions about the interests of a user, using preferences of similar users, or content based filtering that matches the user’s personal preferences with item characteristics. We adopt the content-based approach and propose to use the concept of resolving set that allows to determine the preferences of the users with a very limited number of ratings. We also show how to make recommendations when user ratings are imprecise or inconsistent, and we indicate how to take into account situations where users possibly don’t care about the attribute values of some items. All recommendations are obtained in a few seconds by solving integer programs.
Original language | American English |
---|---|
Pages (from-to) | 153-178 |
Number of pages | 26 |
Journal | Journal of Global Optimization |
Volume | 81 |
Issue number | 1 |
DOIs | |
State | Published - Sep 2021 |
Keywords
- Integer programs
- Recommender systems
- Resolving sets
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Control and Optimization
- Management Science and Operations Research
- Applied Mathematics