Modeling the clickstream across multiple online advertising channels using a binary logit with Bayesian mixture of normals

The evaluation of online marketing activities using standalone metrics does not explain the development of consumer behavior over time, although it is of primary importance to allocate and optimize financial resources among multiple advertising channels. We develop a binary logit model with a Bayesian mixture approach to demonstrate consumer clickstreams across multiple online advertising channels. Therefore, a detailed user-level dataset from a large financial service provider is analyzed. We find both differences in the effects of repeated advertisement exposure across multiple types of display advertising as well as positive effects of interaction between display and paid search advertising influencing consumer click probabilities. We identify two consumer types with different levels of susceptibility to online advertising (resistant vs. susceptible consumers) and show that the knowledge of consumers individual click probabilities can support companies in managing display advertising campaigns. (C) 2013 Elsevier B.V. All rights reserved.