Joint Decision Making

Joint decision-making research explores how to optimally combine decisions from multiple sources, such as humans and AI algorithms, or multiple AI models, to achieve superior outcomes compared to individual decision-makers. Current research focuses on developing frameworks that account for diverse input types (e.g., probabilistic preferences, heterogeneous model predictions), employing techniques like integer linear programming and graph neural networks to integrate and normalize these inputs, and optimizing collaborative strategies to maximize overall performance. This field is significant for improving the efficiency and accuracy of decision-making in various applications, from resource allocation and content recommendation to complex systems planning and human-AI collaboration.