Addressing Interpretability and Cold-Start in Matrix Factorization for Recommender Systems.
Michail VlachosCelestine DünnerReinhard HeckelVassilios G. VassiliadisThomas P. ParnellKubilay AtasuPublished in: IEEE Trans. Knowl. Data Eng. (2019)
Keyphrases
- matrix factorization
- recommender systems
- cold start
- collaborative filtering
- cold start problem
- data sparsity
- low rank
- implicit feedback
- user preferences
- nonnegative matrix factorization
- information overload
- factorization methods
- prediction accuracy
- user generated content
- user profiles
- recommendation quality
- recommendation systems
- tensor factorization
- user interests
- latent factor models
- item recommendation
- personalized recommendation
- user ratings
- user model
- probabilistic matrix factorization
- machine learning
- recommendation algorithms
- user feedback
- user experience
- eye tracking
- information retrieval