AdTheorent, a Real Time Bidding (RTB)-enabled mobile ad network, has launched a white paper describing its patent-pending Real-Time Learning Machine (RTLM), which it claims is the first real-time learning and predictive modelling platform developed specifically for mobile advertising.
Authored by Dr. Saed Sayad, the company’s chief data scientist, the white paper details the key differentiators of AdTheorent’s RTLM, which learns in real-time, generates data-driven predictive models “on the fly” and “predicts faster than any other data mining technology”.
AdTheorent says that RTLM can accurately process data sets including purchase, behavioural, psychographic, ancillary and social data. The company’s proprietary Traktion™ product also measures post-click data, delivering “beyond the click” analytics with post-click conversion data.
RTLM uses a three-stage data analysis approach to refine billions of bid requests. Using RTLM, the company says, 100 different predictive models can be tested in less than one second, and then 80-90 per cent of the irrelevant or uncorrelated variables can be eliminated on the fly. AdTheorent’s says the technology has produced uplift of between 50 and 500 per cent in RTLM-powered mobile ad campaigns.
“We did not invent a new algorithm when we created the RTLM; we merely use data analysis in a different way,” said Dr. Sayad. “Traditional predictive modelling is a much more time-intensive endeavour, and is nowhere near as flexible as the approach that we have created. The real-time learning that is deployed in our system creates massive spikes on top of an existing lift in positive targeting, and this is the breakthrough that has produced the success that we are seeing in campaigns that have used this system.”
You can download the whitepaper here.