AdPalette: an algorithm for customizing online advertisements on the fly

In this paper, we address customization and dynamic optimization of online advertisements. For online ads that attract click-throughs, we use click th rough rates to develop a methodology for customizing advertisements on the fly by changing content, copy, placement, animation and other attributes. W e use techniques from optimization, conjoint analysis and genetic algorithm s. Ads are reconstituted on the fly using graphic files for each level of e ach attribute, much like a painter would use a palette. We show that this a pproach improves response rates, reduces server storage requirements and im proves ad efficiency. (C) 2001 Elsevier Science B.V. All rights reserved.