Credit: Katrin Glückler
Andrej Tschalzev
Research Assistant
University of Mannheim
Institute for Enterprise Systems
L 15, 1–6
68161 Mannheim
Institute for Enterprise Systems
L 15, 1–6
68161 Mannheim
E-mail: andrej.tschalzevuni-mannheim.de
Research Interests
- Machine Learning for Tabular Data
- Evaluation and Benchmark Methodology
- Foundation Models for Structured Data
- Data-Centric AI
Short CV
| Seit 2021 | Research Assistant at the Institute of Enterprise Systems |
|---|---|
| 2018–2021 | Master of Science in Data Science at the University of Mannheim |
| 2014–2018 | Bachelor of Arts in Sociology at the University of Mannheim |
Publications
- Rink, J., Szabo, K., Hoyer, C., Saver, J. L., Nour, M., Audebert, H. J., Kunz, W. G., Froelich, M. F., Heinzl, A., Tschalzev, A., Hoffmann, J., Schoenberg, S. O. and Tollens, F. (2025). Mobile stroke units services in Germany: A cost-effectiveness modeling perspective on catchment zones, operating modes, and staffing. European Journal of Neurology, 32, 1–9.
- Cohausz, L., Tschalzev, A., Bartelt, C. and Stuckenschmidt, H. (2024). Investigating demographic features and their connection to performance, predictions, and fairness in EDM models. Journal of Educational Data Mining, 16, 177–213.
- Marton, S., Lüdtke, S., Bartelt, C., Tschalzev, A. and Stuckenschmidt, H. (2024). Explaining neural networks without access to training data. Machine Learning, 113, 3633-3652.
- Rink, J., Tollens, F., Tschalzev, A., Bartelt, C., Heinzl, A., Hoffmann, J., Schoenberg, S. O., Marzina, A., Sandikci, V., Wiegand, C., Hoyer, C. and Szabo, K. (2024). Establishing an MSU service in a medium-sized German urban area — clinical and economic considerations. Frontiers in Neurology, 15, 1–9.
- Nick, E., Purucker, L., Tschalzev, A., Holzmüller, D., Desai, P. M., Salinas, D. and Hutter, F. (2025). TabArena: A living benchmark for machine learning on tabular data. In , Advances in Neural Information Processing Systems : NeurIPS 2025 (S. 1–66). , NeurIPS: Vancouver, BC.
- Tschalzev, A., Marton, S., Lüdtke, S., Bartelt, C. and Stuckenschmidt, H. (2024). A data-centric perspective on evaluating machine learning models for tabular data. In , Advances in Neural Information Processing Systems 37 (NeurIPS 2024) (S. 95896-95930). , Curran Associates Inc.: Red Hook, NY.
- Tschalzev, A., Nitschke, P., Kirchdorfer, L., Lüdtke, S., Bartelt, C. and Stuckenschmidt, H. (2024). Enabling mixed effects neural networks for diverse, clustered data using Monte Carlo methods. In , Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence: Jeju, 03–09 August 2024 (S. ). , International Joint Conferences on Artificial Intelligence: Jeju, South Korea.
- Cohausz, L., Tschalzev, A., Bartelt, C. and Stuckenschmidt, H. (2023). Investigating the importance of demographic features for EDM-predictions. In , Proceedings of the 16th International Conference on Educational Data Mining (S. 125–136). , International Educational Data Mining Society: Bengaluru, India.
- Tschalzev, A., Purucker, L., Lüdtke, S., Hutter, F., Bartelt, C. and Stuckenschmidt, H. (2025). Unreflected use of tabular data repositories can undermine research quality. The Future of Machine Learning Data Practices and Repositories at ICLR 2025, Singapore, Republic of Singapore.