Bayesian Networks Applications in Decision Support Systems

Decision support systems are designed to help decision makers get a view of the present and the future under alternative scenarios. A decision support system is different from a typical dashboard application designed to represent current conditions and trends using a range of indicators and descriptive statistics. The paper is focused on decision support systems with three case studies. The first case study is about the integration of mobility data of populations available from Google with hospitalization data related to COVID 19. This data is from the pandemic era, and with Bayesian networks, provides an impact assessment of possible non-pharmaceutical interventions such as closure of airports. A second case study is from a usability assessment platform with data based on web surfing characteristics. A third application is a conflict resolution politography application where economic and other types of data are analysed to create a data driven narrative. These three different examples show how Bayesian networks can be used, in different contexts, to support decision support systems. The paper makes the link between decision support systems and Bayesian networks and provides examples of implementation. Section 1 is an introduction to decision support systems, sections 2, 3, and 4 cover the case studies. Section 5 is a concluding section sketching future research pathways.