Leveraging Multiactions to Improve Medical Personalized Ranking for Collaborative Filtering

Table 1

Some notations used in the paper.

Notations	Description
	User set,
	Item set,
	Items (preference of observation over user u’s one kind action)
	Items (preference of observation over user u’s auxiliary action)
	Items (preference of observation),
	Items (absence of observation),
	User index
	Item index
	Pair set (preference of observation over user u’s one kind action),
	Pair set (preference of observation over user u’s auxiliary action),
	Pair set (absence of observation),
	Auxiliary coefficient, ,
	The number which user u has made to item i based on one kind action
	The number which user u has made to item j based on auxiliary action
	Preference of user u on item i
	Model parameters
	User u’s latent feature vector, d is the number of latent factors
	User i’s latent feature vector, d is the number of latent factors
	Item i’s bias