At CODE, we are working on data-based solutions for societal problems involving cognition and behaviour.

Think of a child from a poor family background, not being recognised for its high scholastic potential. Think of a diabetic patient, struggling with adopting a healthy lifestyle or a health professional making a terrible mistake, because of poor usability. Think of the owner of a self-driving car, drowsy after a hard day’s work, or an elderly person, in danger of a hip fracture due to a fall.

CoDE is part of the Department Learning, Data analytics and Technology (LDT) within the Faculty of Behavioural, Management and Social sciences (BMS).


    By collecting data on school achievement, we contribute to measuring educational quality and identifying opportunities for improvement. By integrating and modelling data we measure abilities in order to identify talents and to track perforhumance over time, be that a school kid or a surgeon. We track health-promoting behaviours in patients and give them feedback. By applying algorithms, we use sensory input to signal fatigue in operators of self-driving cars and to stimulate motor learning and balance control in the elderly. By working on fair algorithms we make sure that machine learning is working for the people, not against them. By studying people’s physiological and behavioural responses and how people process information, we help design safer, reliable, and resilient systems enabling people to achieve their goals in an efficient, effective and satisfactory way.


    Behind our data-based approach is a pursuit of both comprehensive explanatory and actionable theoretical models, that are created by crossing boundaries between previously split theoretical sub-disciplines (human factors, educational measurement, machine learning). These actionable models describe and explain the mental and physical processes of the human who lives, behaves and develops within a system, like a human-machine environment, a learning environment, a health environment. When creating solutions for issues that arise in these human-system environments, we need to have a full grasp of these processes, the context and conditions under which they take place, and how they can be supported and improved.

    To realize these ambitions, data collection and analyses inherently need to be multi-modal, multi-level and multi-perspective.


    We have a long history of expertise in psychometric, educational and experimental measurements. We are experts in human factors research and data-driven ergonomics, covering biomechanical, cognitive, and social systems. We are a key player in large national and international educational surveys like PISA, TIMSS and Peil, and we are also working with a broad network of small and large companies. Over the last 15 years, CoDE has acquired expertise in applying machine learning techniques in health and education research. We combine virtual and mixed reality systems with smart sensor arrays and deep learning systems to study the boundaries of complex human systems in the most holistic way.

    Across BMS, CODE plays a key role in teaching research methods, data analysis, cognitive psychology, and ergonomics to bachelor students.  Additionally, our team also teaches text mining, social network analysis, predictive modelling, and biofeedback analysis, where we reap the benefits of our investments in teaching R and linear models. Finally, the MSc track in Human Factors and Engineering Psychology further trains students to proactively tackle real-world problems. This educational approach exemplifies our responsibility in delivering a data-savvy and tech-loving workforce.