AdTheorent, Inc., a technology company whose data-driven predictive solutions are transforming digital advertising, today announced significant advancements to its anti-fraud infrastructure, as well as sample performance statistics over a recent 30-day measurement period. Previously launched last year as a mobile-only solution to identify fraud that went undetected by traditional third party anti-fraud solutions, AdTheorent’s real-time (pre-bid) detection model is now able to identify fraud across all digital environments, maximizing cross-environment brand safety and ad spend.
Now fully deployed to detect fraud on a cross-environment basis, in a recent 30-day period AdTheorent’s anti-fraud infrastructure identified and blocked 70,232,713,950 fraudulent digital impressions. Of those blocked impressions, more than 42 billion derived from non-human or bot behavior (NHT), a frequently cited problem in digital advertising. (Recently, the Association of National Advertisers reported that advertisers will lose an estimated $7.2 billion globally this year as a result of fraudulent impressions, or bots, up $1 billion from last year). During the same period, AdTheorent’s anti-fraud infrastructure also blocked nearly 28 billion impressions originating directly from data centers or servers (as opposed to digital devices such as a mobile phone or laptop). Additionally, AdTheorent’s infrastructure blocked more than 7 million proxy server impressions, which are impressions whose source of origin is masked.
Tapping its robust data-driven predictive modeling platform, AdTheorent uses statistical analysis techniques to identify anomalies and aberrational behavior impacting publisher inventory. Because 35 billion ad requests come through AdTheorent’s systems per day, the Company is able to identify trends across exchanges and identify fraud that other detection solutions don’t have the scale or technical capacity to find. This is automated as part of AdTheorent’s bidder functionality, which allows the fraud to be detected in real time, enabling the company to react immediately, which is extremely beneficial as fraud evolves quickly and often morphs before many companies can identify it. Removing fraud on a pre-bid basis is especially critical because fraudulent properties are typically high performing properties (high CTRs), designed to yield bids from automated systems which optimize higher performing properties.
“Fraud is a tricky and very fluid activity that is changing constantly and is extremely hard for many tools and systems to identify and keep up with,” said Chris Cagle, AdTheorent’s EVP of Technology. “The speed at which our big data mining platform processes data, coupled with our scale, allows us to find and eradicate fraud in real time, across all digital environments. We’re thrilled that in just a one-month period alone, we have identified and blocked more than 70 billion fraudulent impressions.”
Simultaneously, the Company conducts on-going qualitative reviews of web sites and apps within its network, assigning qualitative scores to each property based on property-specific screenings. AdTheorent’s qualitative analysis focuses on identifying low value ad impressions that might not be detectable through statistical algorithms, such as sites optimized to take advantage of “mis-clicks,” or impressions which do not meet brand safety guidelines In all cases and across all environments, properties and devices identified as suspect and potentially fraudulent are filtered from AdTheorent’s inventory before bidding occurs.
AdTheorent’s proprietary fraud-detection algorithms are driven by terabytes of data which identify artificial, non-human behaviors and traffic patterns likely driven or directed by bots, as well as traffic whose source of origin is masked using proxy servers. And most important, because ad fraud, like all fraud, is fluid and dynamic in its forms and shapes, the tools and methods needed to identify fraud as it evolves must be equally dynamic and fluid, and must be able to learn from ever-changing data sets.
Said James Lawson, AdTheorent’s Managing Partner & Chief Legal Officer, “digital ad fraud is the subject of growing interest, including a recent letter to the FTC by Sens. Mark Warner (D-Va.) and Chuck Schumer (D-NY), but AdTheorent engineers and data scientists have been implementing and refining solutions in market for over a year. We view digital ad fraud as a market inefficiency that we are uniquely equipped to combat. Our ability to do deliver reliable impressions to our clients is a key differentiator for AdTheorent.”
AdTheorent is a technology company that is transforming digital advertising through user identity mapping and data-driven predictive solutions. AdTheorent’s machine learning technology platform, Cross-Environment Map and Barometric® technologies help brands understand and connect with their audiences at scale.
AdTheorent’s machine learning technology platform combines millions of data attributes into precise and accurate adaptive models for the purpose of identifying optimal audiences. Powered by data-driven intelligence, AdTheorent’s platform delivers the right ad, to the right user, at the right time – all in “real time” within brand advertisers’ ROAS and performance goals.
AdTheorent provides the most comprehensive cross-environment mapping infrastructure in market, which maps millions of unique device IDs to US households and other physical locations, and appends those device IDs with extensive 1st, 2nd and 3rd party data sources. As a mobile-first Data Management Platform, AdTheorent is uniquely positioned to match offline and online data to mobile at scale, affect cross-environment targeting and break new ground in media attribution including physical activity such as purchase.
AdTheorent’s Barometric measurement and analytics solution features the advertising industry’s most advanced cross-environment tracking and attribution solution, providing the “post-click and post view” signals necessary for modeling to (i.e., predicting) true user engagement and awareness.
The collective result to AdTheorent-partnered brands and marketers is higher engagement rates across any client-defined metric – The Intelligent Impression®. For more information, visit: www.adtheorent.com.