DASS: Digital Advertising System Simulation
Venue
Google Inc. (2016)
Publication Year
2016
Authors
Stephanie Sapp, Jon Vaver, Minghui Shi, Neil Bathia
BibTeX
Abstract
We describe a Digital Advertising System Simulation (DASS) for modeling advertising
and its impact on user behavior. DASS is both flexible and general, and can be
applied to research on a wide range of topics, such as digital attribution, ad
fatigue, campaign optimization, and marketing mix modeling. This paper introduces
the basic DASS simulation framework and illustrates its application to digital
attribution. We show that common position-based attribution models fail to capture
the true causal effects of advertising across several simple scenarios. These
results lay a groundwork for the evaluation of more complex attribution models, and
the development of improved models.
