CUSTOMER RESPONSE MODELS WITH A DELAY FACTOR IN DIRECT MARKETING

摘要

Many growth-curve models are based on simplifying assumptions that are not valid in many practical situations. In the paper, we propose a probabilistic response model that has many desirable properties. Our geometric response model has three meaningful parameters – an ultimate response rate among the recipients, a resistance rate of respondents, and a delay factor. We show that these parameters can be estimated by the method of maximum likelihood. We finally fitted our response model to a mail survey data to show its outstanding performance, which is attributed to the delay factor that describes the delivery and processing time of responses.