The growing reliance on digital infrastructure has exposed financial institutions to increasingly dynamic cyber risks. As regulatory scrutiny and capital adequacy requirements intensify, there is rising demand for models that are both adaptive and interpretable. This paper proposes a hybrid framework that integrates regime-switching econometrics with explainable machine learning to model cyber attack severity in the financial sector. Using a curated subset of global cyber incidents affecting banks, insurers, and FinTech firms, we estimate two-regime Markov Switching Models (MSMs) with autoregressive components to identify latent regime dynamics in monthly incident intensity. Smoothed regime probabilities are then used to condition event-level classification models, allowing predictive relationships to vary across structural phases. Explainability is achieved through Shapley value analysis, enabling regime-specific interpretation of severity drivers. Empirical results identify a regime transition beginning in early 2023, characterized by increased persistence of high-severity activity and a reweighting of technical and actor-related predictors. The findings demonstrate that integrating econometric regime detection with interpretable machine learning provides a coherent and regime-sensitive framework for cyber risk modeling in regulated financial environments.
Giudici, Paolo, Pirra, Marco, Zieni, Rasha. Time-varying explainable AI for cyber risk management in the financial sector: a Markov switching approach. // Annals of Operations Research. – 2026. – DOI: 10.1007/s10479-026-07463-9. – URL: http://link.springer.com/openurl/fulltext?id=doi:10.1007/s10479-026-07463-9
Giudici, Paolo, Pirra, Marco, Zieni, & Rasha (2026). Time-varying explainable AI for cyber risk management in the financial sector: a Markov switching approach. Annals of Operations Research. https://doi.org/10.1007/s10479-026-07463-9
Giudici, et al. “Time-varying explainable AI for cyber risk management in the financial sector: a Markov switching approach.” Annals of Operations Research, 2026. doi:10.1007/s10479-026-07463-9.
@article{Giudici2026,
title = {Time-varying explainable AI for cyber risk management in the financial sector: a Markov switching approach},
author = {Giudici and Paolo and Pirra and Marco and Zieni and Rasha},
journal = {Annals of Operations Research},
year = {2026},
doi = {10.1007/s10479-026-07463-9},
url = {http://link.springer.com/openurl/fulltext?id=doi:10.1007/s10479-026-07463-9}
}
In this paper, we consider cost-sharing problems defined on rooted trees. We refer to these problems as cost-tree problems and to the induced transferable utility cooperative games as irrigation games. We introduce a formal notion of...
In this paper, we focus on nonlinear programming problems with cardinality constraints that restrict the number of nonzero components of the decision vector. We start with a straightforward mixed-integer programming reformulation....
Portfolio selection is a critical issue in financial management under uncertainty. In this paper, we propose a complex approach for portfolio selection with quantile return approximation. In particular, we propose a practical workflow...
The transcendental logarithmic (translog) production function is recognised as a flexible functional form for modelling production processes. It accommodates varying elasticities of input substitution and diverse types of...
This study investigates mothership-drone route determination using two optimization approaches: a Mixed Integer Linear Programming (MILP) model based on a discrete hexagonal grid, and a Mixed Integer Nonlinear Programming (MINLP) model...