Share these talks and lectures with your colleagues
Invite colleaguesResearch paper
Will they stay or will they go? Predicting customer churn in the energy sector
Applied Marketing Analytics: The Peer-Reviewed Journal,
6
(2),
136-150
(2020)
Abstract
The liberalisation of the European energy market has driven changes in the way firms approach marketing, both for the acquisition of new consumers and for retaining existing ones. To retain consumers, practitioners aim to predict which consumers intend to churn (ie leave), and to understand the reasons behind this intention. To address this need, this study uses data-mining techniques to develop a churn prediction model. The study aims to identify the information that is predictive of churn and, consequently, to shed light on the psychological reasons behind churn. The authors built eight predictive models using decision trees, random forest and logistic regression on a dataset composed of 81,813 consumers of an energy provider, each with one residential electricity contract. The logistic regression was found to outperform the other methods. The discussion focuses on the relevant predictors of churn by addressing a posteriori psychological explanations of consumers’ churn behaviour. The study provides new insights on the reasons why customers churn and, by addressing theoretical psychological explanations, provides a data-mining model with robustness to contextual changes.
Keywords: churn prediction model; customer churn; consumer psychology; machine learning; energy market
The full article is available to subscribers to the journal.
Author's Biography
Michela Vezzoli is Postdoctoral Research Fellow in Psychology at Milano-Bicocca University. She has a master’s degree in the psychology of social processes, decision making and financial behaviours as well as a PhD from Milano-Bicocca University. During her PhD, she investigated the psychological processes that underlie customer churn behaviour through the quantitative analysis of consumers’ behaviour using statistical methodologies such as data mining and machine learning.
Cristina Zogmaister is Associate Professor in Psychometrics at the University of Milan Bicocca. She received her degree in psychology as well as her PhD from Padua University. Her research interests span the fields of psychological measurement, implicit social cognition and the prediction of behaviour. Most of her research focuses on implicit attitudes and the prediction of behaviour by way of indirect measures. She is particularly interested in the psychology of consumers’ attitudes, self-concept, wellbeing in the workspace, and the objectification of women in Western cultures.
Dirk Van Den Poel is Full Professor of Marketing at Ghent University. He received his degree in management/business engineering as well as his PhD from K.U. Leuven. His research interests include Big Data, customer intelligence/analytical customer relationship management (including customer acquisition, customer retention, cross/up-selling, credit scoring modelling), business intelligence, marketing analytics, artificial neural networks, data mining, text mining, random forests, random multinomial logit, marketing optimisation and optimal resource allocation.
Citation
Vezzoli, Michela, Zogmaister, Cristina and Van Den Poel, Dirk (2020, October 1). Will they stay or will they go? Predicting customer churn in the energy sector. In the Applied Marketing Analytics: The Peer-Reviewed Journal, Volume 6, Issue 2. https://doi.org/10.69554/HEFD7326.
© Henry Stewart
Publications LLP
Publications LLP