A Bernoulli–Gaussian mixture model of donation likelihood and monetary value: An application to alumni segmentation in a university setting

•We present a finite-mixture model of transaction frequency and monetary value.•We derive an instance of the EM Algorithm to estimate associated parameters.•We analyze transactions and segment donors to a private, research university.•The analysis reveals traits/activities that influence contribution behavior.•The results also reveal significant unobserved heterogeneity in the population.