Methods and systems to evaluate and determine degree of pretense in online advertisement
Systems and methods are provided in the field of online advertising and malicious software. In some embodiments, a method for determining a degree of deceptiveness for a session is provided, the session having one or more relationships between one or more properties of interactions with an online advertisement, the method comprising: extracting one or more characteristics associated with each of the one or more relationships; applying one or more models to each of the one or more relationships to determine a degree of deceptiveness for each of the one or more relationships; aggregating the degree of deceptiveness for each of the one or more relationships to generate the degree of deceptiveness for the session.
1. A method of determining a degree of deceptiveness associated with a session presenting at least one online advertisement, the method comprising:
capturing electronic interactions among at least two entities involved in the session;
defining one or more relationships between the at least two entities involved in the session;
based on the captured electronic interactions, applying one or more models to each of the one or more relationships;
determining a degree of deceptiveness for each of the one or more relationships based on the one or more applied models; and
generating the degree of deceptiveness for the session based on the determined degree of deceptiveness for each of the one or more relationships.
2. The method of claim 1 , wherein the captured interactions include interaction-related properties.
3. The method of claim 2 , wherein the captured interactions further include time.
4. The method of claim 1 , wherein the relationships include an associated set of attributes.
5. The method of claim 1 , further including:
extracting a plurality of attributes for the one or more relationships from the captured electronic interactions, each attribute defining a data type and corresponding data value, wherein the applying the one or more models is based on the extracting.
6. The method of claim 5 , wherein the extraction is performed by integration with the at least two entities.
7. The method of claim 5 , wherein the extracting includes aggregating the plurality of attributes.
8. The method of claim 5 , wherein the extracting includes filtering the plurality of attributes.
9. The method of claim 5 , wherein the extracting includes extracting the plurality of attributes using a tracking pixel.
10. The method of claim 5 , wherein the extracting includes extracting the plurality of attributes using an ad-tracking tag.
11. The method of claim 5 , wherein the extracting includes extracting the plurality of attributes using a cookie.
12. The method of claim 1 , further including:
aggregating the degree of deceptiveness for each of the one or more relationships, wherein the generating the degree of deceptiveness for the session is further based on the aggregated degree of deceptiveness for each of the one or more relationships.
13. The method of claim 12 , wherein aggregating the degree of deceptiveness for each of the one or more relationships includes determining a weighted average of the degree of deceptiveness for each of the one or more relationships.
14. The method of claim 1 , wherein the electronic interactions include at least one of user interactions, web-page rendering of the at least one online advertisement, publisher interactions and advertising network interactions.
15. The method of claim 1 , wherein the one or more models include a model to flag loading the at least one online advertisement on a portion of a web page that is not viewable by a user.
16. The method of claim 1 , wherein the one or more models include an external model associated with one or more predetermined internet addresses, domains, publishers, or advertisers.
17. At least one non-transitory computer readable medium storing instructions that, when executed by a processor, cause the processor to at least:
capture electronic interactions among at least two entities involved in a session presenting at least one online advertisement;
define one or more relationships between the at least two entities involved in the session;
based on the captured electronic interactions, apply one or more models to each of the one or more relationships;
determine a degree of deceptiveness for each of the one or more relationships based on the one or more applied models; and
generate a degree of deceptiveness for the session based on the determined degree of deceptiveness for each of the one or more relationships.
18. The at least one non-transitory computer readable medium of claim 17 , wherein the one or more models include a parametric model.
19. A system for determining a degree of deceptiveness for a session presenting at least one advertisement, the system comprising:
a processor; and
a memory storing instructions that, when executed by the processor, cause the system to:
capture electronic interactions among at least two entities involved in a session presenting at least one online advertisement;
define one or more relationships between the at least two entities involved in the session;
based on the captured electronic interactions, apply one or more models to each of the one or more relationships;
determine a degree of deceptiveness for each of the one or more relationships based on the one or more applied models; and
generate the degree of deceptiveness for the session based on the determined degree of deceptiveness for each of the one or more relationships.
20. The system of claim 19 , wherein the one or more models include a non-parametric model.