About Me

Mark Graus
Maastricht University
BISS Institute

The internet you see is different from the internet I see… Efforts in computer science have resulted in algorithms that allow us to build systems such as personalized search engines, recommender systems and targeted advertising. These systems control the content individual users receive based on how they have behave online. I am an Assistant Professor in Data-Driven Personalization and study the relationship between these personalized systems and peoples’ online behavior and experiences.

My aim is to make data-driven personalization more user-centered. While the main focus on designing these systems lies on the engineering challenges (e.g. how to use historical browsing behavior to infer a user’s movie preferences), implementing these systems and ensuring they actually serve their purpose in helping people comes with numerous design challenges. The way in which I want to overcome these challenges is by adopting a more user-centered perspective, taking into account the users’ psychology and their subjective experience. I believe the only way to successfully create personalized systems is to apply machine learning and incorporate user psychology and user feedback.

This approach is described in more detail in my PhD thesis titled `From behavior-centered to user-centered: incorporating psychological knowledge and user feedback in personalization’.

Academic Positions

  • Present2018

    Assistant Professor

    Maastricht University, Department of Marketing and Supply Chain Management, and BISS Institute, Heerlen

Commercial Roles

  • 20142013

    Data Scientist

    O2mc, Uden, the Netherlands

  • 20132011

    Technical Consultant Online Analytics

    Adversitement, Uden, the Netherlands

Education & Training

  • Ph.D.2018

    PhD in Human-Technology Interaction

    Eindhoven University of Technology

  • M.Sc.2011

    Master of Science in Human-Technology Interaction

    Eindhoven University of Technology

  • B.Sc.2008

    Bachelor of Science in Innovation Sciences

    Eindhoven University of Technology


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 online personalization. While most work in personalization focuses on the machine learning aspects, I feel that it requires 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.

Research Interests

  • Recommender Systems
  • Online Behavior
  • Clickstream Analysis

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.

My 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.


Current Courses

  • Present2018

    Marketing Research Methods

    As part of the Strategic Management master program I teach the quantitative/statistical aspects of doing marketing research

  • Present2019

    Machine Learning for Smart Services

    As part of the Business Intelligence & Smart Services master program I teach students how machine learning can be used to design smart services.

Past Courses

  • 20182018

    Interaction Design

    As part of the Business Intelligence & Smart Services master program I taught students a course in interaction design.


 mp.graus [at] maastrichtuniversity.nl

There are two ways in which I try to make my research and education more valuable: large scale user studies and current, relevant research questions.

Because my research is aimed at technology that aims to serve large, heterogeneous groups of people, I want to ensure that my findings hold up outside of the lab.  I thus try to take the research out of the lab and into the field as much as possible. In addition, I try to ensure that my research addresses problems that people or companies face. As such, I am interested in collaborations with companies or researchers that are interested in doing large scale user experiments. 

In terms of teaching I try to achieve the same. Guest lectures from people that have professional experience give students a perspective I cannot provide, and allow them to understand why they are taught what I am teaching them.

I thus appreciate all opportunities to discuss my research and education, so please contact me if you would like to discuss anything from guest lectures, research opportunities or even would like me to give a talk. Depending on the day of the week, I can be found either in my office in Maastricht University or at BISS Institute in Heerlen.