Online advertising is progressively moving towards a programmatic model inwhich ads are matched to actual interests of individuals collected as theybrowse the web. Letting the huge debate around privacy aside, a very importantquestion in this area, for which little is known, is: How much do advertiserspay to reach an individual? In this study, we develop a first of its kindmethodology for computing exactly that -- the price paid for a web user by thead ecosystem -- and we do that in real time. Our approach is based on tappingon the Real Time Bidding (RTB) protocol to collect cleartext and encryptedprices for winning bids paid by advertisers in order to place targeted ads. Ourmain technical contribution is a method for tallying winning bids even whenthey are encrypted. We achieve this by training a model using as ground truthprices obtained by running our own "probe" ad-campaigns. We design ourmethodology through a browser extension and a back-end server that provides itwith fresh models for encrypted bids. We validate our methodology using a oneyear long trace of 1600 mobile users and demonstrate that it can estimate auser's advertising worth with more than 82% accuracy.
展开▼
