My name is Lea Cohausz and I’m a PhD student specializing in Artificial Intelligence at the University of Mannheim. I am notoriously interested in many things which is reflected in pretty much every aspect of my life.

Research Interests

  • causal modelling and causal structure learning
  • combining causal inference and predictive models
  • XAI and fairness
  • much of the above in the context of Educational Data Mining
  • AI-Planning and Reinforcement Learning for Goal and Plan Recognition

If you are interested in any of these topics, feel free to reach out to me.

Education

  • since 2021: PhD student at the University of Mannheim (Computer Science)
  • 2018-2020: M.Sc. Data Science, University of Mannheim
  • 2018-2021: M.A. Sociology, University of Mannheim

Scholarships

  • 2017-2021: Studienstiftung des deutschen Volkes (German Academic Scholarship Foundation)
  • 2016-2017: Deutschlandstipendium

Publications

Lea Cohausz, Jakob Kappenberger & Heiner Stuckenschmidt. 2024. What fairness metrics can really tell you: A case study in the educational domain. Proceedings of the 14th International Conference on Learning Analytics and Knowledge. Download the Paper here

Lea Cohausz, Andrej Tschalzev, Christian Bartelt & Heiner Stuckenschmidt. 2023. Investigating the Importance of Demographic Features for EDM-Predictions. Proceedings of the 16th International Conference on Educational Data Mining. Download the Paper here Best Student Full Paper Award

Lea Cohausz. 2022. When Probabilities Are Not Enough - A Framework for Causal Explanations of Student Success Models. Journal of Educational Data Mining, 14(3), 52–75. Download the Paper here

Lea Cohausz. 2022. Towards Real Interpretability of Student Success Prediction Combining Methods of XAI and Social Science. Proceedings of the 15th International Conference on Educational Data Mining, 361–367. Download the Paper here Best Student Short Paper Award

Lea Cohausz, Nils Wilken & Heiner Stuckenschmidt. 2022. Plan-Similarity Based Heuristics for Goal Recognition. In 2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops) (pp. 316-321). IEEE.

Nils Wilken, Lea Cohausz, Christian Batelt & Heiner Stuckenschmidt. 2023. Planning Landmark Based Goal Recognition Revisited: Does Using Initial State Landmarks Make Sense?. arXiv preprint arXiv:2306.15362.

Sarah Alturki, Lea Cohausz & Heiner Stuckenschmidt. 2022. Predicting Master’s students’ academic performance: an empirical study in Germany. Smart Learning Environments, 9(1), 1-22. https://doi.org/10.1186/s40561-022-00220-y

Nils Wilken, Lea Cohausz, Johannes Schaum, Stefan Lüdtke, Christian Bartelt and Heiner Stuckenschmidt. 2022. Leveraging Planning Landmarks for Hybrid Online Goal Recognition. ICAPS SPARK.

Teaching

  • Decision Support: Master-level course on the basics of logic and probability theory, graphical models (in particular BNs), utility theory, game theory, and reinforcement learning
  • Industrial Applications of AI (my sessions: agriculture/computer vision and education/XAI/causal modelling and biases): hands-on Master-level course
  • Master Team Project and Master Seminar Content Recommendation

Interests Outside Academia

I enjoy being outside, going on hikes, bouldering, sailing, playing all kinds of sports, and being a volunteer firefighter.

Social Involvement