FraudSensor Overview

FraudSensor is HUMAN’s post-bid solution for detecting fraudulent traffic. By using detection tags to collect signals, FraudSensor can provide traffic analysis at the impression level.

FraudSensor is only capable of providing retroactive analysis for impressions that have already occurred. However, you can also implement FraudSensor in conjunction with MediaGuard for more comprehensive traffic monitoring that both verifies bid requests in real time and provides retroactive traffic analysis. When used at the same time, the combination of FraudSensor and MediaGuard creates a personalized traffic ecosystem that grants you access to the full range of HUMAN’s insight and analysis.

How FraudSensor works

FraudSensor’s detection tags are built using a set of client-supplied parameters. Using the data from these parameters and other signals that are automatically collected from each impression, FraudSensor can determine whether each impression is valid or invalid. Detection tags come in several types to accommodate different use cases and environments.

FraudSensor’s detection engine investigates each event from every applicable device and analyzes thousands of data points, including differences in code, performance characteristics, and other potential indicators of bot-driven behavior. You can access this traffic analysis (including “valid or invalid” decisions and additional traffic statistics) through the HUMAN Dashboard or the Reporting API.