Systems and methods to identify candidates for targeted advertising in an online social gaming environment

A system comprising:

• a prediction model generator to predict a behavior of a second user in an online social gaming environment based on a first degree of influence of a first user in the online social gaming environment on the second user;
• a processor to determine the first degree of influence of the first user on the second user based on first social gaming data corresponding to participation by the first user and the second user in the online social gaming environment during a first period of time, the processor to compare the predicted behavior of the second user to second social gaming data corresponding to participation by the second user in the online social gaming environment during a second period of time after the first period of time, the processor to update the first degree of influence of the first user on the second user based on the comparison, wherein different types of the social gaming data are to be weighted differently when calculating the first degree of influence of the first user on the second user, the different weights based on when the different types of the social gaming data were collected, wherein a first weight of older social gaming data of a first type is to be less than a second weight of newer social gaming data of the first type, wherein the first degree of influence of the first user on the second user is different than a second degree of influence of the second user on the first user;
• a network graph generator to generate a network graph representative of relationships between a plurality of users associated with the online social gaming environment, the relationships based on connections between the users, the plurality of users including the first and second users, the network graph representative of the first degree of influence of the first user on the second user and the second degree of influence of the second user on the first user;
• and
• a target identifier to identify the first user as a candidate for targeted advertising when the first degree of influence satisfies a threshold and to provide information identifying the candidate to at least one of a game publisher, a social gaming service provider, or a third party advertiser.

A tangible computer readable storage medium comprising instructions which, when executed, cause a machine to at least:

• generate a network graph representative of relationships between users associated with an online social gaming environment, the relationships based on connections between the users;
• collect first social gaming data corresponding to participation by a first user and a second user in the online social gaming environment during a first period of time, the first social gaming data including first user data corresponding to the first user and second user data corresponding to the second user;
• calculate a first influence of the first user of the online social gaming environment on the second user of the online social gaming environment, the first influence based on the first social gaming data, the first influence selected from a plurality of different degrees of influence corresponding to different portions of the first user data that match the second user data;
• assign weights to the different portions of the first user data, the weights to decrease over time based on when corresponding ones of the different portions of the first user data were collected;
• calculate a second influence of the first user of the online social gaming environment on a third user of the online social gaming environment;
• calculate a combined influence for the first user based on the first influence of the first user and the second influence of the first user;
• predict a behavior of the second user based on the first influence of the first user on the second user;
• compare the predicted behavior of the second user to second social gaming data corresponding to participation by the second user in the online social gaming environment during a second period of time after the first period of time;
• and
• update the first influence of the first user on the second user based on the comparison;
• identify the first user as a candidate for targeted advertising based on the network graph when the combined influence satisfies a threshold;
• and
• identify the candidate to at least one of a game publisher, a social gaming service provider, or a third party advertiser.