Chapter 2 Introduction

One of the key trends in the advertising industry is (digital) data-driven marketing. The whole thing starts with massive, passive data collection. No matter which website we visit or which app we use: We leave a digital footprint. These footprints are compiled for individual users and form so-called user profiles. A set of similar profiles is then aggregated to user segments, which aim at describing a homogeneous set of users with similar preferences and interests. In order to improve marketing activities, companies use these user segments to show them ads that fit the user’s interest.

Before we dive into the details of data collection and profile generation, let’s have a simplified look at how ad space for individual users is bought.

2.1 Real-time Advertising

If a single user visits a website which provides several advertisements slots, each ad placeholder calls a system called supplied side platform (SSP) and request a suitable ad. The request includes a user id (cookie) and the ad specification such as size, placement on the website and basic information about the website (Domain, Category, Content information). The supply side platform starts an auction to sell the ad placement to the advertiser with the highest bid. Advertisers change their bid price depending on the information they have about the user. For example, an insurance company might want to pay much more for users who are currently looking for a new insurance policy.

To sum up, the technology allows to buy ad slots for individual users in real time. The industry calls this “buying a user”. The key question is how to value each individual user. In order to value individual users it is key to collect as much information (demographics, attitudes, personality, interests,…) as possible about each individual user. The better the information about a user, the better the advertiser can price the ad slot. Next, we detail how information gathering in these systems works.