|
CF categories | Representative techniques | Main advantages | Main shortcomings |
|
Memory-based CF | eighbor-based CF (item-based/user-based CF algorithms with Pearson/vector cosine correlation) | asy implementation |
*are dependent on human ratings |
ew data can be added easily and incrementally |
*performance decrease when data are sparse |
tem-based/user-based top- recommendations | eed not consider the content of the items being recommended |
*cannot recommend for new users and items |
*scale well with co-rated items |
*have limited scalability for large datasets |
|
Model-based CF | ayesian belief nets CF |
*better address the sparsity, scalability and other problems |
*expensive model-building |
lustering CF |
DP-based CF |
*improve prediction performance |
*have trade-off between prediction performance and scalability |
atent semantic CF |
parse factor analysis |
*give an intuitive rationale for recommendations |
*lose useful information for dimensionality reduction techniques |
F using dimensionality reduction techniques, for example, SVD, PCA |
|
Hybrid recommenders | ontent-based CF recommender, for example, Fab |
*overcome limitations of CF and content-based or other recommenders |
*have increased complexity and expense for implementation |
ontent-boosted CF |
*improve prediction performance |
*need external information that usually not available |
ybrid CF combining memory-based and model-based CF algorithms, for example, Personality Diagnosis |
*overcome CF problems such as sparsity and gray sheep | |
|