Click fraud detection
Systems and methods for detecting instances of click fraud are disclosed. Click fraud occurs when, for example, a user, malware, bot, or the like, clicks on a pay per click advertisement (e.g., hyperlink), a paid search listing, or the like without a good faith interest in the underlying subject of the hyperlink. Such fraudulent clicks can be expensive for an advertising sponsor. Statistical information, such as ratios of unpaid clicks to pay per clicks, are extracted from an event database. The statistical information of global data is used as a reference data set to compare to similar statistical information for a local data set under analysis. In one embodiment, when the statistical data sets match relatively well, no click fraud is determined to have occurred, and when the statistical data sets do not match relatively well, click fraud is determined to have occurred.
1. A method comprising:
identifying, by a computing device, a referral to a website, the referral made in response to selection of a referral resource at a search results page of a search engine;
identifying, by the computing device, a search query submitted to the search engine to obtain the search results page;
determining, by the computing device, reference activity data comprising data indicative of a plurality of search queries submitted to the search engine from a plurality of computing devices, the plurality of search queries comprising search queries that are similar to or the same as the search query;
generating, by the computing device, statistical data based at least in part on the reference activity data, the statistical data comprising one or more of a number of the plurality of search queries, a frequency of the plurality of search queries, and variation in usage of the plurality of search queries; and
determining, by the computing device, whether the referral to the website represents click fraud based at least in part on a comparison of the search query to the statistical data.
2. The method of claim 1 , wherein the reference activity data further comprises data indicative of search queries submitted to a plurality of search engines.
3. The method of claim 1 , wherein generating the statistical data comprises recognizing a pattern of the plurality of search queries.
4. The method of claim 3 , wherein generating the statistical data comprises generating a probability distribution of the pattern of the plurality of search queries.
5. The method of claim 1 , further comprising:
identifying, by the computing device, a number of new search queries.
6. The method of claim 5 , further comprising:
identifying, by the computing device, IP addresses of computing devices from which the new search queries were submitted.
7. The method of claim 6 , wherein the computing devices from which the new search queries were submitted comprise code configured to submit the new search queries.
8. A computer-readable storage device having computer-executable instructions embodied thereon, the instructions comprising:
instructions to identify, by a computing device, a referral to a website, the referral made in response to selection of a referral resource at a search results page of a search engine;
instructions to identify, by the computing device, a search query submitted to the search engine to obtain the search results page;
instructions to determine, by the computing device, reference activity data comprising data indicative of a plurality of search queries submitted to the search engine from a plurality of computing devices, the plurality of search queries comprising search queries that are similar to or the same as the search query;
instructions to generate, by the computing device, statistical data based at least in part on the reference activity data, the statistical data comprising one or more of a number of the plurality of search queries, a frequency of the plurality of search queries, and variation in usage of the plurality of search queries; and
instructions to determine, by the computing device, whether the referral to the website represents click fraud based at least in part on a comparison of the search query to the statistical data.
9. The computer-readable storage device of claim 8 , wherein the reference activity data further comprises data indicative of search queries submitted to a plurality of search engines.
10. The computer-readable storage device of claim 8 , wherein the instructions to generate the statistical data comprise instructions to recognize a pattern of the plurality of search queries.
11. The computer-readable storage device of claim 10 , wherein the instructions to generate the statistical data further comprise the instructions to generate a probability distribution of the pattern of the plurality of search queries.
12. The computer-readable storage device of claim 8 , the instructions further comprising:
instructions to identify, by the computing device, a number of new search queries.
13. The computer-readable storage device of claim 12 , further comprising:
identifying, by the computing device, IP addresses of computing devices from which the new search queries were submitted.
14. The computer-readable storage device of claim 13 , wherein the computing devices from which the new search queries were submitted comprise code configured to submit the new search queries.