A Bayesian Networks Approach to Operational Risk

TL;DR

This paper introduces a Bayesian Network-based system for operational risk management in banks, utilizing internal loss data to model process correlations with minimal organizational disruption.

Contribution

It presents a novel algorithm for constructing Bayesian Networks tailored to individual banks using only internal loss data, effectively capturing process correlations.

Findings

Validated on synthetic data demonstrating effectiveness.

Low organizational impact and limited resource requirements.

Capable of modeling correlations among bank processes.

Abstract

A system for Operational Risk management based on the computational paradigm of Bayesian Networks is presented. The algorithm allows the construction of a Bayesian Network targeted for each bank using only internal loss data, and takes into account in a simple and realistic way the correlations among different processes of the bank. The internal losses are averaged over a variable time horizon, so that the correlations at different times are removed, while the correlations at the same time are kept: the averaged losses are thus suitable to perform the learning of the network topology and parameters. The algorithm has been validated on synthetic time series. It should be stressed that the practical implementation of the proposed algorithm has a small impact on the organizational structure of a bank and requires an investment in human resources limited to the computational area.