Personalization involves on the one hand mining or analyzing large amounts of data, which requires a thorough understanding of the current state-of-the-art with regards to algorithms. On the other hand, as personalization aims to help people, it requires both understanding the user and incorporating users in the evaluation.
I want to bridge the gap between machine learning and psychology. More specifically I am interested in combining the possibilities provided by machine learning methods with the fundamental knowledge about people for data-driven personalization. In order to create personalization that truly helps people, I feel that the machine learning models applied require a better incorporation of theoretical knowledge. My goal is to find a right balance in research and avoid either over-simplifying users and over-engineering systems, or vice versa.
- Recommender Systems
- Online Behavior
- Clickstream Analysis
This research direction was established during my master thesis on recommender systems. The observation that current collaborative filtering recommender algorithms share similarities with the way decision making psychologists operationalize preferences lead to a study to see if that similarity can be used to make recommender systems more understandable to their users. This study lead to more work on diversification in recommender systems.
I took the same approach of incorporating theoretical knowledge about users in predictive modeling for the domain of website adaptation. I investigated to what extent we can incorporate knowledge of website owners on their audience in real-time online personalization. Not by only considering the observable behavior, but also relating this behavior to what we (think we) know about the visitors of our websites. This allowed for a more controlled, transparent implementation of the website adaptations, as well as verifying our assumptions about website visitors.