Worth the effort? Comparison of different MCMC algorithms for estimating the Pareto/NBD model

Abstract The Pareto/NBD model is one of the best-known models in customer base analysis. Extant literature has brought up three different Markov Chain Monte Carlo (MCMC) procedures for parameter estimation this model. Nevertheless, main research gaps remain. Firstly, issue hyper sensitivity these been disregarded even though crucial when dealing with small sample sizes. Secondly, present lacks a performance comparison between MCMC as well Maximum Likelihood Estimates (MLE). Thirdly, existing minimal data set requirements neglect they only refer to MLE. To tackle gaps, we perform two extensive simulation studies. We demonstrate that algorithms differ their towards distributions and identify algorithm outperforms other all respects. In addition, provide deeper insights into individual level forecasts using enhance extant limitation guidelines by considering not cohort size but also length calibration period.