D
Dirk Van den Poel
Researcher at Ghent University
Publications - 202
Citations - 9430
Dirk Van den Poel is an academic researcher from Ghent University. The author has contributed to research in topics: Customer relationship management & Customer retention. The author has an hindex of 49, co-authored 200 publications receiving 8368 citations. Previous affiliations of Dirk Van den Poel include Katholieke Universiteit Leuven & The Catholic University of America.
Papers
More filters
Journal ArticleDOI
Customer attrition analysis for financial services using proportional hazard models
Dirk Van den Poel,Bart Larivière +1 more
TL;DR: These findings suggest that: (1) demographic characteristics, environmental changes and stimulating ‘interactive and continuous’ relationships with customers are of major concern when considering retention; (2) customer behaviour predictors only have a limited impact on attrition in terms of total products owned as well as the interpurchase time.
Journal ArticleDOI
Customer base analysis: partial defection of behaviourally loyal clients in a non-contractual FMCG retail setting
Wouter Buckinx,Dirk Van den Poel +1 more
TL;DR: In this paper, the authors focus on the treatment of a company's most behaviorally loyal customers in a non-contractual setting and build a model in order to predict partial defection by behaviourally loyal clients using three classification techniques: Logistic regression, automatic relevance determination (ARD) Neural Networks and Random Forests.
Journal ArticleDOI
Churn prediction in subscription services: An application of support vector machines while comparing two parameter-selection techniques
TL;DR: In this article, support vector machines were applied to a newspaper subscription context in order to construct a churn model with a higher predictive performance, and a comparison is made between two parameter selection techniques, needed to implement support vector machine.
Journal ArticleDOI
Evaluating multiple classifiers for stock price direction prediction
TL;DR: The results indicate that Random Forest is the top algorithm followed by Support Vector Machines, Kernel Factory, AdaBoost, Neural Networks, K-Nearest Neighbors and Logistic Regression in the domain of stock price direction prediction.
Journal ArticleDOI
Consumer Acceptance of the Internet as a Channel of Distribution
Dirk Van den Poel,Joseph Leunis +1 more
TL;DR: In this paper, the viability of the World Wide Web (WWW) as a channel of distribution is investigated and two research questions are studied: (1) comparison of two non-store retailing channels with two store channels, and (2) consumer reaction when channel functions are transferred to the Internet.