Unintrusive customization techniques for Web advertising

Marc Langheinrich, Atsuyoshi Nakamura, Naoki Abe, Tomonari Kamba, Yoshiyuki Koseki
Computer Networks

Add Remove

abstract Most online advertisement systems in place today use the concept of consumer targeting: each user is identified and, according to his or her system setup, browsing habits and available off-line information, categorized in order to customize the advertisements for highest user responsiveness. This constant monitoring of a user’s online habits, together with the trend to centralize this data and link it with other databases, continuously nurtures fears about the growing lack of privacy in a networked society. In this paper, we propose a novel technique of adapting online advertisement to a user’s short term interests in a non-intrusive way. As a proof-of-concept we implemented a dynamic advertisement selection system able to deliver customized advertisements to users of an online search service or Web directory. No user-specific data elements are collected or stored at any time. Initial experiments indicate that the system is able to improve the average click-through rate substantially compared to random selection methods. on 6/10/2019, 9:38:26 AM

excerpt We can categorize current approaches to online advertisement into four categories [4]: Untargeted. Early systems and many small scale operations in use today simply target the broad Web audience in general. Ads are either fixed on a Web page for a certain time period and then manually updated, or a simple, random form of banner rotation is used [15]. Editorial. Ad banners are targeted to a certain site or page topic. For example, advertisers on the Yahoo! [23] Web site can target their advertisement to any of the more than 100 thousand categories featured in the Web directory. Targeted (filtered). The most popular form of professional Web advertising today. Advertisers can specify targeting parameters such as the user’s operating system or browser software, time constraints, country or even the Internet service provider (ISP) used. The selection mechanism on the ad server (step 5 in Fig. 2) analyzes the request and selects only those advertisements for placement that match the current situation. Personalized. Next generation advertisement systems use neural networks [2] and other proprietary learning methods [7] to allow personalized advertisement selection based on the browsing and interaction history of a particular history of a particular history of a particular user, as well as other demographic information. 183 on 6/10/2019, 9:42:22 AM


Targeted advertising with inventory management cites Unintrusive customization techniques for Web advertising on 6/10/2019, 9:38:03 AM