Probabilistic and statistical modelling for risk evaluation

Financial systemic risk This area addresses the formidable challenges posed by risk transmission within vast, interconnected economic and financial systems. The papers collectively highlight the need for dynamic models that can capture unexpected shocks and their propagation. Research here explores risk transmission in volatile commodity markets (“The motifs of risk transmission in multivariate time series: application to commodity prices”, by Paolo Pagnottoni and Alessandro Spelta), and the intricate link between Public health and pandemic contexts The recent global health crisis underscored the critical importance of risk modelling in healthcare and public policy. Papers in this section focus on measuring and managing health-related risks, often utilising real-world data to address urgent needs. This includes predicting and explaining absenteeism risk in hospital patients before and during COVID-19 (“Predicting and Explaining Absenteeism Risk in Hospital Patients Before and During COVID-19” by Ana Borges, Mariana Carvalho, Miguel Maia, Operational, mobility, and logistical risk This theme shifts the focus to the practical, operational challenges of risk management in complex logistical and service systems. The research spans both global and local scales. At a humanitarian level, papers demonstrate how tools like FMEA and grey relational analysis can enhance risk management in humanitarian supply chains (“Risk management in humanitarian supply chain based on FMEA and grey relational analysis” by Glenda Minguito, and Jenith Banluta), by combining Failure Mode and Societal risk and human dynamics Risk is not solely an economic or technical construct; it is deeply embedded in societal structures and human behaviour. This section examines risks that directly impact social welfare, security, and human capital. This includes quantifying the negative effect of organised crime (Mafia risk perception) on firm efficiency and investment, blending institutional risk with firm behaviour (“Mafia risk perception: evaluating the effect of organized crime on firm technical efficiency and investment Advanced methodologies: machine learning, networks, and scenario planning A key takeaway from this special issue is the methodological evolution of risk science. Several papers are dedicated to, or heavily rely upon, sophisticated computational tools. The application of Machine Learning is prominent, demonstrated by a direct comparison of classification models (“Machine learning classification model comparison” by Paolo Giudici, Alex Gramegna, and Emanuela Raffinetti) and their empirical use in assessing Credit Risk for small and mid-sized businesses