Share these talks and lectures with your colleagues
Invite colleaguesResearch paper
The benefits of Shapley-value in key-driver analysis
Applied Marketing Analytics: The Peer-Reviewed Journal,
6
(3),
269-278
(2021)
Abstract
Linear (and other types of) regression are often used in what is referred to as ‘driver modelling’ in customer satisfaction studies. The goal of such research is often to determine the relative importance of various sub-components of the product or service in terms of predicting and explaining overall satisfaction. Driver modelling can also be used to determine the drivers of value, likelihood to recommend, etc. A common problem is that the independent variables are correlated, making it difficult to get a good estimate of the importance of the ‘drivers’. This problem is well known under conditions of severe multicollinearity, and alternatives like the Shapley-value approach have been proposed to mitigate this issue. This paper shows that Shapley-value may even have benefits in conditions of mild collinearity. The study compares linear regression, random forests and gradient boosting with the Shapley-value approach to regression and shows that the results are more consistent with bivariate correlations. However, Shapley-value regression does result in a small decrease in k-fold validation results.
Keywords: driver modelling; regression; Shapley-value; customer satisfaction; random forests; gradient boosting
The full article is available to subscribers to the journal.
Author's Biography
Marco Vriens has a PhD in marketing analytics and is a recognised expert in applied analytics. He led analytics teams for Microsoft, GE and supplier firms. Marco is the author of three books: ‘The Insights Advantage: Knowing How to Win’ (2012), ‘Handbook of Marketing Research’ (2006) and ‘Conjoint Analysis in Marketing’ (1995). Marco has been published in academic and industry journals and has won several best paper awards including the David K. Hardin Award.
Chad Vidden has a PhD in Applied Mathematics, with expertise in computational mathematics, data science and machine learning. He is currently an assistant professor at the University of Wisconsin – La Crosse, where he leads a data science and mathematical modelling research group that collaborates with local companies.
Nathan Bosch is a master’s student in machine learning at the KTH Royal Institute of Technology in Stockholm. He has a bachelor’s degree in artificial intelligence from the University of Groningen. His research interests include system log file analysis, predictive maintenance and business analytics. He has also worked in applied machine learning.
Citation
Vriens, Marco, Vidden, Chad and Bosch, Nathan (2021, January 1). The benefits of Shapley-value in key-driver analysis. In the Applied Marketing Analytics: The Peer-Reviewed Journal, Volume 6, Issue 3. https://doi.org/10.69554/KDDQ4647.
© Henry Stewart
Publications LLP
Publications LLP