USER INTEREST AND RELATIONSHIP DETERMINATION
In one example in accordance with the present disclosure, a method for user interest and relationship determination may include distributing a first and a second set of pairs to a plurality of data nodes. The method may also include calculating, on a first data node, a probability of a user's interest in a product based on an observable factor and a latent factor and calculating, on second data node, a probability of a likelihood of a relationship between the user and a second user, based on an observable factor and a latent factor. The method may also include determining a most likely interest and a most likely relationship of the user and predicting a potential interest of the user based on the most likely interest and the most likely relationship.
1 . A method comprising:
distributing a first set of pairs and a second set of pairs to a plurality of data nodes, wherein each pair in the first set of pairs is of a user of a social network and a product on the social network and each pair in the second set of pairs defines a connection between users on the social network;
calculating, on a first data node belonging to the plurality of data nodes, a first probability of a first user's interest in a first product based on a first observable factor and a first latent factor, wherein the first user and the first product belong to a first pair from the first set of pairs;
calculating, on a second data node, a second probability of a likelihood of a relationship between the first user and a second user, based on a second observable factor and a second latent factor, wherein the first user and the second user belong to a second pair from the second set of pairs;
determining, based on the first probability and the second probability, a most likely interest of the first user and a most likely relationship of the first user; and
predicting a potential interest of the first user based on the most likely interest and the most likely relationship,
2 . The method of claim 2 wherein the first pair and the second pair are used as a first input key and a second input key, respectively, for a map function, the first observable factor and the first latent factor are used as values for the first input key and the second observable factor and the second latent factor are used as values for the second input key.
3 . The method of claim 2 , further comprising
generating, based on the first probability and the second probability, a triplet including two users from the social network and a product that at least one of the two users has expressed interest in on the social network.
4 . The method of claim 3 , further comprising:
maximizing an objective function corresponding to the triplet, wherein a first parameter of the objective function corresponds to the most likely interest of the first user and a second parameter of the objective function corresponds to the most likely relationship of the first user.
5 . The method of claim 4 , wherein the objective function is maximized using a stochastic gradient descent.
6 . The method of claim 1 further comprising:
determining a probability distribution of the first user's interest in the first product and the relationship between the first user and the second user.
7 . The method of claim 6 , wherein a user-interest-user triplet is used as an input key for a reduce function and the probability distribution is used as a value for the input key.
8 . The method of claim 7 , further comprising:
distributing each pair in the first set of pairs and the second pairs to the plurality of data nodes, wherein each data node in the plurality of data nodes processes a pair; and
merging a result of processing by the plurality of data nodes using the triplet as a key so that all values using the same triplet are grouped together.
9 . A system comprising:
a first probability calculator to calculate, on a first data node, a first probability of a first user's interest in a first product based on a first observable factor and a first latent factor;
a second probability calculator to calculate, on a second data node, a second probability of a likelihood of a relationship between the first user and a second user based on a second observable factor and a second latent factor;
an interest and relationship determiner to determine, based on the first probability and the second probability, a most likely interest of the first user and a most likely relationship of the first user;
triplet generator to generate, based on the first probability and the second probability, a triplet including two users from the social network and a product that at least one of the two users has expressed interest in on the social network; and
a relationship predictor to predict a potential relationship of the first user based on the most likely interest and the most likely relationship.
10 . The system of claim 9 wherein the first user and the first product are used as a first input key and the first user and the second user are used as a second input key for a map function, the first observable factor and the first latent factor are used as values the first input key and the second observable factor and the second latent factor are used as values for the second input key.
11 . The system of claim 9 wherein the triplet is used as an input key for a reduce function and a value for the input key is a probability distribution of the first user's interest in the first product and the relationship between the first user and the second user.
12 . A non-transitory machine-readable storage medium encoded with instructions, the instructions executable by a processor of a system to cause the system to:
distribute a first set of pairs and a second set of pairs to a plurality of data nodes, wherein each pair in the first set of pairs is of a user of a social network and a product on the social network and each pair in the second set of pairs defines a connection between users on the social network;
determine, on the plurality of data nodes, a probability distribution of a first user's interest in a first product and a relationship between the first user and a second user, wherein the probability is based on an observable factor and a latent factor;
generate, based on the probability distribution, a triplet including two users from the social network and an interest product that at least one of the two users has expressed interest in on the social network;
determine, based on the probability distribution, a most likely interest of the first user and a most likely relationship of the first user; and
predict a potential interest of the first user based on the most likely interest and the most likely relationship.
13 . The non-transitory machine-readable storage medium of claim 12 wherein the triplet is used as an input key for a reduce function and the probability distribution is used as a value for the input key.
14 . The non-transitory machine-readable storage medium of claim 12 , wherein the instructions executable by the processor of the system further cause the system to:
maximize an objective function corresponding to the triplet, wherein a first parameter of the objective function corresponds to the most likely interest of the first user and a second parameter of the objective function corresponds to the most likely relationship of the first user.
15 . The non-transitory machine-readable storage medium of claim 12 , wherein the instructions executable by the processor of the system further cause the system to:
distribute each pair in the first set of pairs and the second pairs to the plurality of data nodes, wherein each data node in the plurality of data nodes processes a pair; and
merge a result of processing by the plurality of data nodes using the triplet as a key so that all values using the same triplet are grouped together.