Inferring the presence of an entity within an identifier space based on the behaviors of unrelated entities
Embodiments of the invention build models to predict the likelihood of entities that operate in a given identifier space also operating in a disjoined identifier space based on a source panel of entities that operate in one or both of the identifier spaces. In operation, a model building engine builds a model based on features associated with the source panel and features associated with standard populations in the given identifier space. The model is used to determine whether the target entity is more similar to those entities in the source panel that operate only in the given identifier space or those entities in the source panel that operate in both identifier spaces.
1. A method comprising:
identifying an archetypical set of entities that operate in a first identifier space and do not operate in a second identifier space, the archetypical set of entities having a first criteria;
identifying a standard set of entities that operate in a first identifier space and do not operate in a second identifier space, at least one of the standard set of entities not having the first criteria;
identifying a combined set of entities that operate in the first identifier space and operate in the second identifier space;
identifying a first set of features that distinguishes the archetypical set of entities from the standard population and identifying a second set of features that distinguishes the combined set of entities from the standard population;
building a model associated with the first identifier space based on the first set of features and the second set of features;
applying the model to a target entity that operates in the first identifier space to determine a likelihood that the target entity also operates in the second identifier space; and
responsive to the likelihood being high, serving an advertisement having content specific to the second identifier space to the target entity in the first identifier space.
2. The method of claim 1 , wherein the first identifier space is an internet browser space and the second identifier space is a mobile identifier space.
3. The method of claim 1 , wherein the first identifier space is an internet browser space and the second identifier space is a digital television space.
4. The method of claim 1 , wherein the first identifier space is an internet browser space and the second identifier space is gaming system space.
5. The method of claim 1 , wherein the first identifier space is an internet browser space and the second identifier space is an in-vehicle system space.
6. The method of claim 1 , wherein the first identifier space is an internet browser space and the second identifier space is a platform user login space.
7. The method of claim 1 , wherein the first identifier space is an internet browser space and the second identifier space is an offline identifier space.
8. The method of claim 1 , wherein the first identifier space is a mobile identifier space and the second identifier space is an internet browser space.
9. The method of claim 1 , wherein applying the model to the target entity comprises:
computing a first score indicative of the similarity between the target entity and the archetypical set of entities by comparing a consumption history associated with the target entity with the first set of features;
computing a second score indicative of the similarity between the target entity and the combined set of entities by comparing a consumption history associated with the target entity with the second set of features;
comparing the first score and the second score to determine the likelihood of the target entity also operating in the second identifier space, wherein the first score being higher than the second score indicates that the likelihood of the target entity also operating in the second identifier space is lower than when the second score is higher than the first score.
10. A non-transitory computer readable storage medium storing processor-executable instructions, the instructions configured to be executed by the processor to implement a method comprising:
identifying an archetypical set of entities that operate in a first identifier space and do not operate in a second identifier space, the archetypical set of entities having a first criteria;
identifying a standard set of entities that operate in a first identifier space and do not operate in a second identifier space, at least one of the standard set of entities not having the first criteria;
identifying a combined set of entities that operate in the first identifier space and operate in the second identifier space;
identifying a first set of features that distinguishes the archetypical set of entities from the standard population and identifying a second set of features that distinguishes the combined set of entities from the standard population;
building a model associated with the first identifier space based on the first set of features and the second set of features;
applying the model to a target entity that operates in the first identifier space to determine a likelihood that the target entity also operates in the second identifier space; and
responsive to the likelihood being high, serving an advertisement having content specific to the second identifier space to the target entity in the first identifier space.
11. The medium of claim 10 , wherein the first identifier space is an internet browser space and the second identifier space is a mobile identifier space.
12. The medium of claim 10 , wherein the first identifier space is an internet browser space and the second identifier space is a digital television space.
13. The medium of claim 10 , wherein the first identifier space is an internet browser space and the second identifier space is gaming system space.
14. The medium of claim 10 , wherein the first identifier space is an internet browser space and the second identifier space is an in-vehicle system space.
15. The medium of claim 10 , wherein the first identifier space is an internet browser space and the second identifier space is a platform user login space.
16. The medium of claim 10 , wherein the first identifier space is an internet browser space and the second identifier space is an offline identifier space.
17. The medium of claim 10 , wherein the first identifier space is a mobile identifier space and the second identifier space is an internet browser space.
18. The medium of claim 10 , wherein applying the model to the target entity comprises:
computing a first score indicative of the similarity between the target entity and the first set of entities by comparing a consumption history associated with the target entity with the first set of features;
computing a second score indicative of the similarity between the target entity and the second set of entities by comparing a consumption history associated with the target entity with the second set of features;
comparing the first score and the second score to determine the likelihood of the target entity also operating in the second identifier space, wherein the first score being higher than the second score indicates that the likelihood of the target entity also operating in the second identifier space is lower than when the second score is higher than the first score.
19. A system comprising:
a processor; and
a computer readable storage medium storing processor-executable computer program instructions, the computer program instructions comprising instructions for:
identifying an archetypical set of entities that operate in a first identifier space and do not operate in a second identifier space, the archetypical set of entities having a first criteria;
identifying a standard set of entities that operate in a first identifier space and do not operate in a second identifier space, at least one of the standard set of entities not having the first criteria;
identifying a combined set of entities that operate in the first identifier space and operate in the second identifier space;
identifying a first set of features that distinguishes the archetypical set of entities from the standard population and identifying a second set of features that distinguishes the combined set of entities from the standard population;
building a model associated with the first identifier space based on the first set of features and the second set of features;
applying the model to a target entity that operates in the first identifier space to determine a likelihood that the target entity also operates in the second identifier space; and
responsive to the likelihood being high, serving an advertisement having content specific to the second identifier space to the target entity in the first identifier space.
20. The system of claim 19 , wherein the first identifier space is an internet browser space and the second identifier space is a mobile identifier space.