Identifying representative users in matrix factorization-based recommender systems: application to solving the content-less new item cold-start problem.
Marharyta AleksandrovaArmelle BrunAnne BoyerOleg ChertovPublished in: J. Intell. Inf. Syst. (2017)
Keyphrases
- cold start problem
- matrix factorization
- recommender systems
- collaborative filtering
- data sparsity
- cold start
- item based collaborative filtering
- item recommendation
- low rank
- missing data
- user generated content
- implicit feedback
- nonnegative matrix factorization
- user interests
- user preferences
- personalized recommendation
- user ratings
- factorization methods
- information overload
- web search
- probabilistic matrix factorization
- rating prediction
- data sparseness
- recommendation algorithms
- user model