Monash University

Restricted Access

Reason: Access restricted by the author. A copy can be requested for private research and study by contacting your institution's library service. This copy cannot be republished

Modelling customer churn in non-contractual settings

posted on 2017-02-16, 03:02 authored by Tamaddoni Jahromi, Ali
In today’s increasingly saturated and highly competitive markets, customers have become more demanding and more likely to switch between companies. In response, astute companies acknowledge that their business strategies should focus on identifying those customers who are most likely to ‘churn’ (defect) and then use the outcome of this prediction to design the appropriate churn management campaigns. In this regard, the current study contributes to literature on churn modelling in non-contractual settings by investigating the performance of different primary churn modelling approaches to find an optimum approach based not only on its accuracy (from a lift measure perspective) but also on its ability to maximize the profitability of a churn management campaign. In addition, it proposes a data-mining approach to model non-contractual customer churn in B2B contexts. The constructed model is then used to demonstrate the profit that the company can make by implementing such predictive models in a B2B churn management campaign. Finally, the study improves the existing profitability framework of churn management campaigns by modelling the probability of accepting an incentive as dependent on its monetary value, using an exponential distribution functional link. The resulting model has the ability to maximize the profit of the campaign on an aggregate level as well as the individual level, by optimizing the incentive value offered to a given customer.


Campus location


Principal supervisor

Stanislav Stakhovych

Year of Award


Department, School or Centre

Monash University. Faculty of Business and Economics. Department of Marketing


Doctor of Philosophy

Degree Type



Faculty of Business and Economics

Usage metrics

    Faculty of Business and Economics Theses


    No categories selected