Description

Measuring Online Behavioural Advertising: The Tale of the Data Transparency Lab and Other Adventure

In simple terms, behavioural targeting is segmentation based on customer behaviours. It provides the ability to organize customers based on various variables related to their behaviours, such as the number of visits they have made to our online store, what products they have bought, what categories they prefer, if they have registered as a member or not, etc. You can also establish what should be done after certain behaviours are observed.

In this lecture, Nikolaos Laoutaris will describe the methods that they have developed to audit: Web domains for behavioural targeting by training artificial "personas", individual impression by using only browser history and online taxonomies for web-pages, and individual impression by using crowdsourced data from multiple users.

He will also present his initial findings on the amount of targeting going on, the most targeted categories, the existence of targeting even in sensitive personal categories for which the law requires explicit user consent, as well as our results on identifying the chain of companies involved in the delivery of such ads. Going beyond online advertising, he will also present earlier work on detecting online price discrimination as well as his community building efforts in setting up and growing the Data Transparency Lab.