Our Impact


Attitudinal perspectives for predicting churn

Attitudinal perspectives for predicting churn by Dr. Duane Varan

MediaScience is the leading provider of lab-based media and advertising research, incorporating a range of neuro-measures including biometrics, facial expression analysis, eye tracking, EEG, and more. With state-of-the-art labs in New York, Chicago, and Austin, MediaScience is discovering actionable insights in advertising, technology, media, and consumer trends.

Dr. Duane Varan, the global authority of neuromarketing research, founded Audience Labs (formerly the Interactive Television Research Institute) during his tenure at Murdoch University in Perth, Australia, in 2001. In 2005, he launched the Beyond : 30 Project, a consortium exploring the changing media and advertising landscape, and in 2008, he was approached by Disney Media Networks to set up a dedicated custom research lab on a broader scale – and so MediaScience was born. Though he officially left Murdoch in 2015, he continues to maintain some research links with the University of South Australia and has been widely recognised for his innovative contributions to teaching and the neuromarketing industry as evidenced by a long list of awards and over 90 published academic papers in his field.

Below is an abstract from one of his papers about Attitudinal perspectives for predicting churn from the Journal of Research in Interactive Marketing.


As acquiring new customers is costly, putting effort into satisfying and keeping customers over the long term can improve profitability. Firms usually do not know how each individual customer is feeling at any time (their attitude to the firm), so typically a customer’s likelihood of leaving (“churning”) is predicted from behavioural data. The purpose of this paper is to investigate how a firm can add attitudinal variables to these churning models by deriving proxy indicators of satisfaction and commitment from behavioural data. The paper tests whether adding these proxies improved predictions of churning compared to a typical model based on purchasing behaviour (PB).

Analysing data from 6,000 regular customers from an Australian digital versatile disc rental company, logistic regression predicted membership termination (i.e. churning=1) versus continuation (=0). A baseline model used three traditional behavioural variables directly linked to members’ PB. A second model including proxies for satisfaction and commitment from the customer database was compared against the baseline model to investigate improvement in churn prediction.

The most significant predictor of churn is an indicator of commitment: the uncertainty of a customer’s commitment, indicated by number of times they changed their subscription plan.

Practical implications
The more customers change their plan, the more likely they are to quit the relationship with the firm, most likely because they are uncertain about how they can benefit from a long‐term commitment to the firm. Monitoring uncertainty indicators, such as plan changing, allows firms to intervene with special offers for uncertain customers, and, therefore, increase the likelihood of them staying with the firm.

The paper discusses the use of customer behaviour recorded in databases to identify proxy indicators of attitude before this attitude translates into churning behaviour.

Zorn, S., Jarvis, W. and Bellman, S. (2010), “Attitudinal perspectives for predicting churn”, Journal of Research in Interactive Marketing, Vol. 4 No. 2, pp. 157-169.