Understanding the Economic Determinants of the Severity of Operational Losses: A regularized Generalized Pareto Regression Approach,

We investigate a novel database of 10,217 extreme operational losses from the Italian
bank UniCredit, covering a period of 10 years and 7 di erent event types. Our goal
is to shed light on the dependence between the severity distribution of these losses
and a set of macroeconomic, financial and fi rm-speci c factors. To do so, we use
Generalized Pareto regression techniques, where both the scale and shape parameters
are assumed to be functions of these explanatory variables. In this complex distributional
regression framework, we perform the selection of the relevant covariates with a
state-of-the-art penalized-likelihood estimation procedure relying on L1-norm penalty
terms of the coefficients. A simulation study indicates that this approach efficiently
selects covariates of interest but also tackles spurious regression issues encountered
when dealing with integrated time series of covariates. The results of our empirical
analysis have important implications in terms of risk management and regulatory policy.
In particular, we found that high unemployment rate and low economic growth
are associated with smaller probabilities of extreme severities, whereas high volatility
on the financial market is associated with more extreme losses. Looking at firm
speci c factors, a commercial strategy driven by non-interest incomes is associated
with an increased likelihood of extreme severities. Last, we illustrate the impact of
several economic scenarios on the requested capital of the total operational loss, and
find important discrepancies across loss types and scenarios.