RTB House, a technology company specializing in retargeting scenarios, has come up with a brand new model that relies on deep learning (currently the most promising subfield of AI-oriented research) to craft digital features that recognize the attitude, intention and intent of internet users. It allows for accurate estimation of the conversion probability, which in turn makes personalized retargeting more efficient than before. The model can even be applied to users who haven’t clicked ads, a long-sought after feature of digital marketers.
Users take hundreds of small steps when visiting advertiser’s website. The model developed by RTB House uses deep learning to identify every one of these footprints, in order to find patterns in decision-making. With a larger pool of relational data, RTB House’s new method can help businesses estimate the individual conversion rate (CR), maximizing return on investment at the earliest possible moment.
The technology uses a mathematical model inspired by the biological neurons in our brains (a so called artificial neural network), which makes it possible to get more reliable, richer, machine-interpretable user descriptions of customer’s buying potential without any human expertise. Conversion rate algorithms collect and interpret not only click data, but take into consideration also how users browse particular offers, categories of interest, basket behaviour or search tactics to have a broader picture of every individual’s buying potential.
Bartlomiej Romanski, CTO of RTB House (pictured top left), notes that conversion prediction (the estimated probability that a user will act in a desired way) plays a crucial role in digital advertising: “We live in a world where big data is comprised of endless streams of information about internet users. Deep understanding of a customer’s needs and attitudes is the first path to success. We’ve used the newest technologies to construct an algorithm which, by using recurrent neural network (deep learning architecture), is able to accurately predict how will internet user behave, what purchase intentions they have, and what decision they will take. This in turn makes our personalized ads even more accurately targeted, bringing our clients higher ROI and helping them use advertising budgets more efficiently.”
RTB House is one of few companies in the world that managed to develop and implement its own technology for purchasing advertisements in the RTB model (real-time bidding) – a solution in which buyers participate in real-time advertising space auctions. The company operates worldwide and currently runs 850 unique campaigns for global brands in almost 40 markets across Europe, Latin America, Asia and Pacific, Middle East and Africa. The RTB team is made up of over 150 people: performance marketing experts, analysts, sales and customer care specialists, programmers and others.
The general idea and results of RTB House deep learning approach were first time presented during an online advertising workshop, part of The 33rd International Conference on Machine Learning (ICML 2016) in New York City.