SOM clustering collaborative filtering algorithm based on singular value decomposition

  • Xiaopan Ma
  • , Xiaojing Li
  • , Dong Guo
  • , Lixin Cui
  • , Xuru Jiang
  • , Xin Chen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The application of traditional collaborative filtering algorithm on large-scale commercial websites is very mature. However, the data sparsity and extensibility problems that occur in the algorithm affect the recommendation accuracy of the algorithm. In order to solve this problem, a SOM clustering collaborative filtering algorithm based on singular value decomposition is proposed. Firstly, the original sparse matrix is reduced by the singular value decomposition, and the items are evaluated in the low-dimensional space, the prediction results are filled in the original matrix, which alleviates the problem of data sparseness. Then use SOM to cluster the users, which reduces the range of users searching for neighbors and improves the scalability of the algorithm. The experimental results on MovieLens-100k show that the algorithm can effectively improve the accuracy of the recommendation.

Original languageEnglish
Title of host publicationICMAI 2019 - Proceedings of 2019 4th International Conference on Mathematics and Artificial Intelligence
PublisherAssociation for Computing Machinery
Pages61-65
Number of pages5
ISBN (Electronic)9781450362580
DOIs
Publication statusPublished - 12 Apr 2019
Externally publishedYes
Event4th International Conference on Mathematics and Artificial Intelligence, ICMAI 2019 - Chegndu, China
Duration: 12 Apr 201915 Apr 2019

Publication series

NameACM International Conference Proceeding Series

Conference

Conference4th International Conference on Mathematics and Artificial Intelligence, ICMAI 2019
Country/TerritoryChina
CityChegndu
Period12/04/1915/04/19

Keywords

  • Collaborative filtering algorithm
  • Recommendation algorithm
  • Self organizing map
  • Singular value decomposition

Fingerprint

Dive into the research topics of 'SOM clustering collaborative filtering algorithm based on singular value decomposition'. Together they form a unique fingerprint.

Cite this