Real-Time Evaluation of Email Campaign Performance

We develop a testing methodology that can be used to predict the performance of email marketing campaigns in real time. We propose a split-hazard model that makes use of a time transformation (a concept we call virtual time) that allows for the estimation of straightforward parametric hazard functions to generate early predictions of an individual campaign's performance (as measured by open and click rates). We apply our method to 25 email campaigns and find that the method is able to produce in less than two hours estimates that are more accurate and more reliable than what the traditional method (doubling time) can produce after 14 hours. Other benefits of our method are that we make testing independent of the time of day and we produce meaningful confidence intervals. Thus, our methodology can be used not only for testing purposes, but also for live monitoring. We show that a campaign selection rule based on our model rather than on the doubling method can improve overall response rates by 20%