Journal article
Rating-Based Collaborative Filtering: Algorithms and Evaluation
Lecture notes in computer science, v 10100, pp 344-390
01 Jan 2018
Abstract
Recommender systems help users find information by recommending content that a user might not know about, but will hopefully like. Rating-based collaborative filtering recommender systems do this by finding patterns that are consistent across the ratings of other users. These patterns can be used on their own, or in conjunction with other forms of social information access to identify and recommend content that a user might like. This chapter reviews the concepts, algorithms, and means of evaluation that are at the core of collaborative filtering research and practice. While there are many recommendation algorithms, the ones we cover serve as the basis for much of past and present algorithm development. After presenting these algorithms we present examples of two more recent directions in recommendation algorithms: learning-to-rank and ensemble recommendation algorithms. We finish by describing how collaborative filtering algorithms can be evaluated, and listing available resources and datasets to support further experimentation. The goal of this chapter is to provide the basis of knowledge needed for readers to explore more advanced topics in recommendation.
Metrics
Details
- Title
- Rating-Based Collaborative Filtering: Algorithms and Evaluation
- Creators
- Daniel Kluver - University of MinnesotaMichael D. Ekstrand - Boise State UniversityJoseph A. Konstan - University of Minnesota
- Contributors
- P Brusilovsky (Editor)D He (Editor)
- Publication Details
- Lecture notes in computer science, v 10100, pp 344-390
- Series
- Lecture Notes in Computer Science
- Publisher
- Springer Nature
- Number of pages
- 47
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Information Science
- Web of Science ID
- WOS:000449409000011
- Scopus ID
- 2-s2.0-85046711637
- Other Identifier
- 3319900927; 9783319900926; 991021818497004721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- Web of Science research areas
- Communication
- Computer Science, Theory & Methods
- Information Science & Library Science
- Social Sciences, Interdisciplinary