System and method for detecting fraudulent activity on client devices
A method, a system, and an article are provided for detecting and managing anomalies associated with content presentations. An example computer-implemented method can include: obtaining a stream of data including a record of clicks on a plurality of client devices; aggregating the stream of data to generate a batch click stream for each of the client devices; processing the stream of data using a real-time anomaly detector to detect a first anomaly indicating that at least one of the client devices was previously associated with fraudulent clicks; processing each batch click stream using a batch anomaly detector to detect a second anomaly indicating that at least one of the batch click streams includes fraudulent clicks; and facilitating an adjustment of content presentations on the client devices, based on at least one of the detected first anomaly and the detected second anomaly.
1. A computer-implemented method, comprising:
obtaining a stream of data comprising a record of clicks generated by users on a plurality of user client devices;
aggregating the stream of data by user client device to generate a batch click stream for each of the user client devices,
wherein each batch click stream comprises click data for clicks generated on an individual user client device from the plurality of user client devices;
processing the stream of data using a real-time anomaly detector to detect a first anomaly indicating that at least one of the user client devices was previously associated with fraudulent clicks;
processing the batch click stream for each user client device using a batch anomaly detector to detect a second anomaly indicating that at least one of the batch click streams comprises fraudulent clicks; and
facilitating an adjustment of content presentations on the user client devices, based on at least one of the detected first anomaly and the detected second anomaly.
2. The method of claim 1 , wherein the stream of data comprises a real-time click stream.
3. The method of claim 1 , wherein the record of clicks comprises a timestamp and a client device identifier.
4. The method of claim 1 , wherein processing the stream of data comprises:
sending each click record to the real-time anomaly detector when the click record is obtained.
5. The method of claim 1 , wherein processing the stream of data comprises:
determining that a device blacklist identifies the at least one of the user client devices.
6. The method of claim 1 , wherein processing each batch click stream comprises:
sending a batch of click records for one of the user client devices to the batch anomaly detector,
wherein the batch anomaly detector comprises a plurality of detection algorithms, and wherein each detection algorithm is configured to detect at least one distinct anomaly from a plurality of detectable anomalies.
7. The method of claim 1 , wherein at least one of the user client devices comprises a mobile device on which clicks were generated by at least one of the users.
8. The method of claim 7 , wherein processing each batch click stream comprises:
selecting, for each batch click stream, at least one detection algorithm from the plurality of detection algorithms.
9. The method of claim 1 , wherein facilitating the adjustment comprises preventing at least one publisher from presenting content on the user client devices.
10. The method of claim 1 , further comprising:
identifying at least one of the user client devices as being associated with the second anomaly; and
adding the identified at least one of the user client devices to a blacklist.
11. A system, comprising:
one or more computer processors programmed to perform operations comprising:
obtaining a stream of data comprising a record of clicks generated by users on a plurality of user client devices;
aggregating the stream of data by user client device to generate a batch click stream for each of the user client devices,
wherein each batch click stream comprises click data for clicks generated on an individual user client device from the plurality of user client devices;
processing the stream of data using a real-time anomaly detector to detect a first anomaly indicating that at least one of the user client devices was previously associated with fraudulent clicks;
processing the batch click stream for each user client device using a batch anomaly detector to detect a second anomaly indicating that at least one of the batch click streams comprises fraudulent clicks; and
facilitating an adjustment of content presentations on the user client devices, based on at least one of the detected first anomaly and the detected second anomaly.
12. The system of claim 11 , wherein the stream of data comprises a real-time click stream.
13. The system of claim 11 , wherein processing the stream of data comprises:
sending each click record to the real-time anomaly detector when the click record is obtained.
14. The system of claim 11 , wherein processing the stream of data comprises:
determining that a device blacklist identifies the at least one of the user client devices.
15. The system of claim 11 , wherein processing each batch click stream comprises:
sending a batch of click records for one of the user client devices to the batch anomaly detector,
wherein the batch anomaly detector comprises a plurality of detection algorithms, and wherein each detection algorithm is configured to detect at least one distinct anomaly from a plurality of detectable anomalies.
16. The system of claim 11 , wherein at least one of the user client devices comprises a mobile device on which clicks were generated by at least one of the users.
17. The system of claim 16 , wherein processing each batch click stream comprises:
selecting, for each batch click stream, at least one detection algorithm from the plurality of detection algorithms.
18. The system of claim 11 , wherein facilitating the adjustment comprises preventing at least one publisher from presenting content on the user client devices.
19. The system of claim 11 , further comprising:
identifying at least one of the user client devices as being associated with the second anomaly; and
adding the identified at least one of the user client devices to a blacklist.
20. An article, comprising:
a non-transitory computer-readable medium having instructions stored thereon that, when executed by one or more computer processors, cause the computer processors to perform operations comprising:
obtaining a stream of data comprising a record of clicks generated by users on a plurality of user client devices;
aggregating the stream of data by user client device to generate a batch click stream for each of the user client devices,
wherein each batch click stream comprises click data for clicks generated on an individual user client device from the plurality of user client devices;
processing the stream of data using a real-time anomaly detector to detect a first anomaly indicating that at least one of the user client devices was previously associated with fraudulent clicks;
processing the batch click stream for each user client device using a batch anomaly detector to detect a second anomaly indicating that at least one of the batch click streams comprises fraudulent clicks; and
facilitating an adjustment of content presentations on the user client devices, based on at least one of the detected first anomaly and the detected second anomaly.