Placement Laundering Fraud


listen on castbox.fmlisten on google podcastslisten on player.fmlisten on pocketcastslisten on podcast addictlisten on tuninlisten on Amazon Musiclisten on Stitcher

--:--
--:--


2022-12-15

Placement Laundering Fraud

On the show today, we speak with Jeff Kline on placement laundering fraud in the ad tech space. Jeff is a Ph.D. holder in Mathematics from the University of Wisconsin with a focus on convex optimization.

Jeff began with a background into what ad fraud and placement laundering were. To put it simply, placement laundering involves placing an ad on a less premium website when the advertiser paid for it to be placed on a premium one. He discussed the technicalities of engaging in placement laundering fraud. He also spoke about how they detected these kinds of frauds.

Jeff discussed how attribution in the ad tech space has moved from the use of refer to other means such as an API-enabled iframe called the safeframe. He explained how attribution through safeframe works. He also discussed the source of placement laundering fraud.

Jeff spoke about the data he used for his analysis. Traffic on a server can be measured using different ways. He mentioned players such as Comscore that help track web traffic which is useful in measuring the attribution of an ad. He detailed the process of identifying placement laundering fraud through the mismatch between the campaign data and the panelist data.

Jeff spoke about how analysts can identify anomalies in the ad data stream. He also discussed reasons laundering fraud is still thriving and possible solutions to the problem. Rounding up, he spoke about how to possibly quantify the magnitude of placement laundering fraud. You can follow Jeff on LinkedIn.

Jeff Kline

Jeff has held managing, lead, senior, and principal data scientist roles in a variety of industries including ad tech, digital media measurement, insurance, and finance. He has published dozens of papers in top journals and conferences on a range of topics including convex optimization, linear algebra, number theory, discrete optimization, internet measurement, and machine learning, and he is co-author on several patents. Early in his career, Jeff developed the data replication software that was used by the LIGO Scientific Collaboration. Jeff received his Ph.D. in Mathematics from the University of Wisconsin–Madison.