A cutting edge model of user behavior that predicts the likelihood of ad clicks and conversions
Build a behavior model that for a given user and product predicts the likelihood that the user will click an ad of this product, or/and will purchase it.
RTB House is one of the first retargeting companies in the world that developed and implemented a proprietary technology based entirely on DL solutions for the purchase of RTB ads. In 2018, the company was ranked eighth among technology companies in the Financial Times 1000:
Europe’s Fastest-Growing Companies 2018, won the Silver Stevie® Award as the most innovative company of the year and received the AIconics Award in the Best Application of AI for Sales & Marketing category and Big Innovation Award granted by the Business Intelligence Group.
Our algorithm made it possible to accurately predict user actions, which is a key component of RTB House technology.
In other words, for a given user and product, we need to predict the likelihood that the user will click on the ad of this product. Our job was to test a variety of models including neural networks, gradient boosting, random forests, factorization machines and various types of regression. We used many techniques, such as k-NN-related functions obtained with LSH (locality-sensitive hashing).
Our LSH regression is available open source in the Practical Approximation Algorithms Library (PAAL)! The solution was created by verifying various hypotheses and testing many different ideas. The cooperation contributed to the rapid development of RTB House and the global success in the online advertising market!
Revenue increase of 14.2 percent with the same percentage of gross margin and reduction of required resources.