When user interactions with an online platform are spoofed, e.g., by the use of automated interactive agents or bots that mimic user behavior, such platform is negatively affected, e.g., may lose ad revenue. This disclosure describes techniques to selectively collect signals from interactive sessions and use the collected signals to determine whether an interactive session is a genuine user session of a human user, or an automated interactive session. The collected signals can include static and/or dynamic signals and are matched to a session identifier. The signals are inspected to assign quality scores and the session is determined as a genuine session based on the quality scores of signals associated with it and the values of those signals. The signal collection techniques described herein can also be utilized for other purposes.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Anonymous, "Intelligent Signal Collection for Detection of Automated Interactive Session", Technical Disclosure Commons, (October 18, 2019)