AI for Decision-Making (AI4DM) develops methods, techniques and tools for AI-driven decision making in operational business process. This involves advanced analysis of business process and optimization of operational decisions in logistics, manufacturing, e-commerce, and healthcare.
Specific tools, methods, and techniques that are being developed include:
- tools for intelligent decision support for humans, using different modalities of data from multiple sources;
- methods for data-driven optimization through AI and ML;
- tools for information management;
- methods for fairness and transparency in decision making;
- methods for data-driven process model discovery, monitoring and redesign;
- methods for automating integration of machine learning and knowledge based models; and
- techniques for explainable AI based on interpretable data driven models for human decision making.
The work focuses on the interplay of machine learning, optimization, and interpretability. These techniques are integrated in decision making pipelines that facilitate their joint use as well as the joint use of techniques from other research clusters.