Dr. Stefan Haas

Research Focus

Stefan was an external Ph.D. candidate pursuing an on-the-job doctorate at BMW. His research is driven by an automotive use case at BMW (goodwill assessment) which serves as an example of prescriptive machine learning. Accordingly, he focuses on key challenges in this area, such as weak supervision and uncertainty quantification.

Publications

• Haas, S., & Hüllermeier, E. (2026). Aleatoric and epistemic uncertainty measures for ordinal classification through binary reduction. Machine Learning, 115(3), 63.
  
• Haas, S., & Hüllermeier, E. (2025). Uncertainty quantification in ordinal classification: A comparison of measures. International Journal of Approximate Reasoning, 186, 109479.
  
• Haas, S., & Hüllermeier, E. (2025). Conformalized prescriptive machine learning for uncertainty-aware automated decision making: the case of goodwill requests. International Journal of Data Science and Analytics, 20(3), 2061-2077.
  
• Haas, S., Hegestweiler, K., Rapp, M., Muschalik, M., & Hüllermeier, E. (2024). Stakeholder-centric explanations for black-box decisions: an XAI process model and its application to automotive goodwill assessments. Frontiers in Artificial Intelligence, 7, 1471208.
  
• Haas, S., & Hüllermeier, E. (2023, September). Rectifying bias in ordinal observational data using unimodal label smoothing. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases (pp. 3-18). Cham: Springer Nature Switzerland.
  
• Haas, S., & Hüllermeier, E. (2022, September). A prescriptive machine learning approach for assessing goodwill in the automotive domain. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases (pp. 170-184). Cham: Springer Nature Switzerland.