Decision Support System
Decision support systems (DSS) aim to augment human decision-making by integrating data analysis and computational models to provide informed recommendations. Current research emphasizes improving the explainability and trustworthiness of DSS outputs, often employing machine learning models like Bayesian networks, decision trees, and transformer-based language models, alongside techniques like counterfactual explanations and conformal prediction sets to enhance user understanding and trust. These advancements are impacting diverse fields, from healthcare diagnostics and treatment planning to resource allocation in areas like forest fire management and infrastructure maintenance, improving efficiency and potentially mitigating risks associated with complex decision-making processes.
Papers
Binary Gaussian Copula Synthesis: A Novel Data Augmentation Technique to Advance ML-based Clinical Decision Support Systems for Early Prediction of Dialysis Among CKD Patients
Hamed Khosravi, Srinjoy Das, Abdullah Al-Mamun, Imtiaz Ahmed
Evaluating and Correcting Performative Effects of Decision Support Systems via Causal Domain Shift
Philip Boeken, Onno Zoeter, Joris M. Mooij