Back to Search
Start Over
An improved collaborative filtering recommendation algorithm based on factor of credit
- Source :
- 2009 IEEE International Conference on Network Infrastructure and Digital Content.
- Publication Year :
- 2009
- Publisher :
- IEEE, 2009.
-
Abstract
- Traditional collaborative filtering algorithm is a weighted average prediction algorithm based on nearest neighbors' ratings. Besides similarity between users, trust and credit are also parameters to affect recommendation. This paper proposes a computational model of credit factor and then a collaborative filtering algorithm based on it. This model is based on trust factor and takes credit model as the basic elements. This proposed algorithm further improves the validity and accuracy of the recommendation.
- Subjects :
- Collaborative software
Artificial neural network
business.industry
Computer science
Recommender system
Machine learning
computer.software_genre
k-nearest neighbors algorithm
Similarity (network science)
Factor (programming language)
Collaborative filtering
Artificial intelligence
Data mining
business
computer
Weighted arithmetic mean
Algorithm
computer.programming_language
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- 2009 IEEE International Conference on Network Infrastructure and Digital Content
- Accession number :
- edsair.doi...........d0bb18e868e58ce68a28adbd28063f62