Prof. Dr. Dr. Marco Ragni

Welcome to the Professorship of Predictive Analytics!

Predictive behavioral analytics – Modeling and analyzing human behavioral data to learn what happened and why it happened and then predict future developments which can help with making appropriate decisions.

Using data science, cognitive modeling, symbolic (e.g. automated planning) and subsymbolic (e.g. ML/statistical models) AI approaches we aim to learn about and understand human behavior in various situations. We work towards simulating human thoughts or reasoning processes in order to predict future scenarios.

We apply our methods in the fields of:
Reasoning - we model human reasoning processes and predict their responses in the syllogistic ^[1], conditional ^[2] and spatial ^[3] domain;
Complex Problem Solving - we examine what predicts human performance in complex problem solving ^[4] and we aim to understand the process of hypothesis generation and collecting strategies;
Algorithmic Thinking - we develop complexity metrics and predict the difficulty and success of mental simulations of algorithms ^[5];
Human Factors in Autonomous Driving - we model human experience (e.g. discomfort) in simulated autonomous driving and predict their reactions in future events ^[6];
Metacognition and Motivation - we study how distraction affects learning and try to predict how well people's learning is there affected by different personality profiles;
Information Retrieval - we focus on modeling the user's knowledge state in information retrieval and its relevance for personalized information retrieval systems using eye-tracking.

For more information, please look at our research webpages and our research assistants' personal pages.

Address

Technische Universität Chemnitz
Professur Prädiktive Verhaltensanalyse
Thüringer Weg 11
09126 Chemnitz

_{[1] Brand, D., Riesterer, N., & Ragni, M. (2020). Extending TransSet: An Individualized Model for Human Syllogistic Reasoning. In Proceedings of the 18th International Conference on Cognitive Modeling.
[2] Todorovikj, S. & Ragni, M. (2021). How good can an individual's conclusion endorsement be predicted?. In Proceedings of the 19th International Conference on Cognitive Modeling.
[3] Ragni, M., Brand, D., & Riesterer, N. (2021). The Predictive Power of Spatial Relational Reasoning Models: A New Evaluation Approach. Frontiers in Psychology, 12. doi: 10.3389/fpsyg.2021.626292.
[4] Heinrich, E. M., & Ragni, M. (2023). The Impact of Personality for Solving Complex Problems. In Proceedings of the Annual Meeting of the Cognitive Science Society (Vol. 45, No. 45). (Abstract)
[5] Todorovikj, S., Brand, D., & Ragni, M. (2022). Predicting Algorithmic Complexity for Individuals. In Proceedings of the 20th International Conference on Cognitive Modeling.
[6] Todorovikj, S., Kettner, F., Brand, D., Beggiato, M., & Ragni, M. (2022). Predicting Individual Discomfort in Autonomous Driving. In Proceedings of the 44th Annual Meeting of the Cognitive Science Society.}