Research Article
Improving POI Recommendation via Dynamic Tensor Completion
| | Model | Scale | Description |
| | Matrix factorization (MF) | | MF is widely used in CF and usually set as baseline. | | Probabilistic matrix factorization (PMF) | | PMF is a conventional model in recommendation domain. | | Factorized personalized Markov chain (FBMC) | | FBMC formalizes the user’s preference as a personalized Markov chain. | | Tucker decomposition (TD) | | TD transforms the high-dimension tensor into a core tensor with a relative matrix in each dimension. | | Canonical polyadic decomposition (CD) | | CD transforms the high-dimension tensor into a multiple equation of linear complexity. | | Time-aware FBMC (TA-FBMC) | | TA-FBMC equips the time factor with the FBMC. | | Time-aware decay FBMC (TAD-FMPC) | | TAD-FMPC adds decay of the probability over time in TA-FBMC. | | Static prido (s-Prido) | | s-Prido removes the dynamic tensor structure from Prido. |
|
|
