Improving purchasing behavior predictions by data augmentation with situational variables
Baecke, Philippe Van den Poel, Dirk
Baecke, Philippe
Van den Poel, Dirk
Citations
Altmetric:
Publication Type
Journal article
Editor
Supervisor
Publication Year
2010
Journal
International Journal of Information Technology & Decision Making
Book
Publication Volume
9
Publication Issue
6
Publication Begin page
883
Publication End page
872
Publication NUmber of pages
Collections
Abstract
Nowadays, an increasing number of information technology tools are implemented in order to support decision making about marketing strategies and improve customer relationship management (CRM). Consequently, an improvement in CRM can be obtained by enhancing the databases on which these information technology tools are based. This study shows that data augmentation with situational variables of the purchase occasion can significantly improve purchasing behavior predictions for a home vending company. Three dimensions of situational variables are examined: physical surroundings, temporal perspective and social surroundings respectively represented by weather, time, and salesperson variables. The smallest, but still significant, increase in predictive performance was measured by enhancing the model with time variables. Besides the moment of the day, this study shows that the incorporation of weather variables, and more specifically sunshine, can also improve the accuracy of a CRM model. Finally, the best improvement in purchasing behavior predictions was obtained by taking the salesperson effect into account using a multilevel model.
Research Projects
Organizational Units
Journal Issue
Keywords
Marketing & Sales