Mathematics of Operations Research
Using Bayesian Networks to Manage Uncertainty in Student Modeling
User Modeling and User-Adapted Interaction
Modeling Elementary Cognitive Abilities for Adaptive Hypermedia Presentation
User Modeling and User-Adapted Interaction
Automatic cognitive style identification of digital library users for personalization
Journal of the American Society for Information Science and Technology
Personalizing influence diagrams: applying online learning strategies to dialogue management
User Modeling and User-Adapted Interaction
Modeling Online Browsing and Path Analysis Using Clickstream Data
Marketing Science
The Impact of Utility Balance and Endogeneity in Conjoint Analysis
Marketing Science
Finite dimensional algorithms for the hidden Markov model multi-armed bandit problem
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 05
A multifactor approach to student model evaluation
User Modeling and User-Adapted Interaction
A Hidden Markov Model of Customer Relationship Dynamics
Marketing Science
Multi-armed bandit algorithms and empirical evaluation
ECML'05 Proceedings of the 16th European conference on Machine Learning
Commentary---Discussion of “Website Morphing”
Marketing Science
Commentary---Discussion of the Article “Website Morphing”
Marketing Science
Proceedings of the third ACM conference on Recommender systems
The Perils of Behavior-Based Personalization
Marketing Science
Editorial---People of Marketing Science
Marketing Science
Predictive analytics in information systems research
MIS Quarterly
Proceedings of the 13th ACM Conference on Electronic Commerce
Explaining the user experience of recommender systems
User Modeling and User-Adapted Interaction
Proceedings of the 13th International Conference on Electronic Commerce
Semi-automatic generation of recommendation processes and their GUIs
Proceedings of the 2013 international conference on Intelligent user interfaces
| Hi-index | 0.00 |
Virtual advisors often increase sales for those customers who find such online advice to be convenient and helpful. However, other customers take a more active role in their purchase decisions and prefer more detailed data. In general, we expect that websites are more preferred and increase sales if their characteristics (e.g., more detailed data) match customers' cognitive styles (e.g., more analytic). “Morphing” involves automatically matching the basic “look and feel” of a website, not just the content, to cognitive styles. We infer cognitive styles from clickstream data with Bayesian updating. We then balance exploration (learning how morphing affects purchase probabilities) with exploitation (maximizing short-term sales) by solving a dynamic program (partially observable Markov decision process). The solution is made feasible in real time with expected Gittins indices. We apply the Bayesian updating and dynamic programming to an experimental BT Group (formerly British Telecom) website using data from 835 priming respondents. If we had perfect information on cognitive styles, the optimal “morph” assignments would increase purchase intentions by 21%. When cognitive styles are partially observable, dynamic programming does almost as well---purchase intentions can increase by almost 20%. If implemented system-wide, such increases represent approximately $80 million in additional revenue.