Severity Of Operational Losses Research Articles

Impacts of the COVID-19 pandemic on operational losses

The main objective of the present study was to determine whether the COVID-19 pandemic impacted the frequency and severity of financial institutions' operational losses. We selected four types of operational-risk events and, applying linear regression, concluded that the pandemic impacted the severity of operational losses. In terms of the frequency of operational losses, we observed no statistically significant difference between pre- and postpandemic losses; however, regarding the severity of losses, we observed an increase in the postpandemic period for the aggregate data, and when analyzing the types of operational-risk events individually, we observed that the frequency of some events increased and others decreased after the pandemic, necessitating a detailed investigation into the reasons for the increase or decrease in the severity of losses.

Understanding the economic determinants of the severity of operational losses: A regularized generalized Pareto regression approach

SummaryWe investigate a novel database of 10,217 extreme operational losses from the Italian bank UniCredit. Our goal is to shed light on the dependence between the severity distribution of these losses and a set of macroeconomic, financial, and firm‐specific 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. We perform the selection of the relevant covariates with a state‐of‐the‐art penalized‐likelihood estimation procedure relying onL1‐penalty terms. A simulation study indicates that this approach efficiently selects covariates of interest and tackles spurious regression issues encountered when dealing with integrated time series. Lastly, we illustrate the impact of different economic scenarios on the requested capital for operational risk. Our results have important implications in terms of risk management and regulatory policy.

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 different 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 firm-specific 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-penalty terms. A simulation study indicates that this approach efficiently selects covariates of interest and tackles spurious regression issues encountered when dealing with integrated time series. The results of our empirical analysis have important implications in terms of risk management and regulatory policy. In particular, we found that high Italian unemployment rate and low GDP growth rate in the European Union are associated with smaller probabilities of extreme severities, whereas high values of the VIX and high growth rates of housing prices are associated with more extreme losses. Looking at firm-specific factors, low leverage ratio and high deposit growth rate are associated with a higher likelihood of extreme losses. Lastly, we illustrate the impact of different economic scenarios on the requested capital for operational risk. We find important discrepancies across event types and scenarios.

Problems of modelling operational loss severity in commercial banking

Problems of modelling operational loss severity in commercial banking

Governance indicators as determinants of operational risk

A country-level model is presented whereby operational loss severity is explained in terms of the size of the economy and governance indicators. Estimation and simulation results show that the average severity of operational losses is positively related to the size of the economy as measured by GDP and that improvement in governance indicators leads to a reduction in the severity of losses. The effect of governance indicators on operational risk can be attributed to the fact that these indicators pertain to the provision of deterrence against crime and to corporate governance, which has implications for internal controls within firms.

Bayesian estimation of truncated data with applications to operational risk measurement

Data insufficiency and reporting threshold are two main issues in operational risk modelling. When these conditions are present, maximum likelihood estimation (MLE) may produce very poor parameter estimates. In this study, we first investigate four methods to estimate the parameters of truncated distributions for small samples—MLE, expectation-maximization algorithm, penalized likelihood estimators, and Bayesian methods. Without any proper prior information, Jeffreys’ prior for truncated distributions is used. Based on a simulation study for the log-normal distribution, we find that the Bayesian method gives much more credible and reliable estimates than the MLE method. Finally, an application to the operational loss severity estimation using real data is conducted using the truncated log-normal and log-gamma distributions. With the Bayesian method, the loss distribution parameters and value-at-risk measure for every cell with loss data can be estimated separately for internal and external data. Moreover, confidence intervals for the Bayesian estimates are obtained via a bootstrap method.

The frequency and severity of operational losses: a cross-country comparison

We examine the proposition that cross-country differences in the factors determining the frequency and severity of operational losses lead to cross-country differences in the distribution and incidence of operational loss events in terms of frequency and severity. For this purpose, we consider 4388 operational loss events covering 11 countries or country groups. The results reveal differences with respect to the type of loss events prevailing in each country or country group as well as differences with respect to the dominance of events of certain type in a particular business line and corporate entity type.

The determinants of frequency and severity of operational losses in Tunisian insurance industry

PurposeThe purpose of this paper is to examine the determinants of operational losses in insurance companies.Design/methodology/approachBy using most common estimates of frequency and severity of losses that affected business‐lines during 2009, the paper integrates a quantitative aspect that reflects the mode of organization in the insurance company. In this paper, it would be more appropriate to focus on the frequency and severity of losses estimated by insurers and which are related to each category of operational risk events that took place in 2009.FindingsThe paper finds that the frequency of operational losses is positively related to the Market Share (MARKSHARE) and the Rate of Geographic Location (RAGELOC). However, the occurrence of loss is negatively related to the Variety of Insurance Activities (VARIACT). The paper also found a decrease in the frequency of losses associated with a large number of employees. Therefore, there is a significant relationship between the Human Factor (HF) and the occurrence of operational losses. In terms of severity, the empirical study has shown that the probability of zero intensity of operational losses is negatively influenced by the Market Share (MARKSHARE) and the Rate of Geographic Location (RAGELOC). In the same framework, the Variety of Insurance Activities (VARIACT) has a negative effect on the probability of high operational loss severity.Originality/valueDespite the absence of the quantitative data of operational risk, this article will discover a new research perspective to estimate the frequency and severity of operational losses in the insurance sector in Tunisia.

A scaling model for severity of operational losses using generalized additive models for location scale and shape (GAMLSS)

AbstractIn this paper, we investigate the problem of how to combine operational losses collected from various banks of different sizes and loss reporting thresholds in order to estimate the distribution of operational loss severities for a bank of a given size. We model the severity of operational losses by using the extreme value theory to account for the reporting bias of the external data, and a regression analysis based on the GAMLSS framework to model the scaling properties of operational losses. In contrast to previous studies on the scaling problem, our analysis gives particular emphasis to the scaling properties of the tail of the loss distribution. Contrary to existing knowledge, we find that the size of a bank is an important determinant of the severity of operational losses and that the tail index of the distribution is negatively correlated with the size of the bank. The results indicate that for very large banks, distribution of the operational loss severity can be extremely heavy tailed (i.e. tail index less than 1), a finding which have significant implications for capital calculation as well as for risk management. Furthermore, we also demonstrate that the capital estimates provided by our model is consistent with the industry standards and the model can be used by individual banks to simulate data to complement their internal data.

Macroenvironmental determinants of operational loss severity

We investigate the relationships between the severity of operational loss events reported in the banking sector and various regulatory, legal, geographical, and economic indicators. Based on a data sample of over 57,000 losses incurred in more than 130 countries reported by the Operational Riskdata eXchange (ORX) consortium, we identify the most relevant exposure indicators for losses in four Basel II event categories: Internal Fraud; External Fraud; Employment Practices and Workplace Safety; and Clients, Products and Business Practices. We find evidence of significant correlations between Internal Fraud and constraints on executive power and the prevalence of insider trading. Clients, Products and Business Practices losses are significantly related to securities and shareholder protection laws, restrictions on banking activity, supervisory power, and the prevalence of insider trading. Other event types are sensitive to per-capita GDP and a governance index.

Modeling Operational Loss Severity Distributions from Consortium Data

Modeling Operational Loss Severity Distributions from Consortium Data

A Scaling Model for Severity of Operational Losses Using Generalized Additive Models for Location Scale and Shape (GAMLSS)

In this paper, we investigate the problem of how to combine operational losses collected from various banks of different sizes and loss reporting thresholds in order to estimate the distribution of operational loss severities for a bank of a given size. We model the severity of operational losses by using the extreme value theory to account for the reporting bias of the external data, and a regression analysis based on the GAMLSS framework to model the scaling properties of operational losses. In contrast to previous studies on the scaling problem, our analysis give particular emphasis to the scaling properties of the tail of the loss distribution. Contrary to existing knowledge, we find that the size of a bank is an important determinant of the severity of operational losses and that the tail index of the distribution is negatively correlated with the size of the bank. The results indicate that for very large banks distribution of the operational loss severity can be extremely heavy tailed (i.e. tail index less than 1), a finding which have significant implications for capital calculation as well as for risk management. Furthermore, we also demonstrate the capital estimates provided by our model is consistent with the industry standards and the model can be used by individual banks to simulate data to complement their internal data.

Basel II and Operational Risk: Implications for Risk Measurement and Management in the Financial Sector

This paper proposes a methodology to analyze the implications of the Advanced Measurement Approach (AMA) for the assessment of operational risk put forward by the Basel II Accord. The methodology relies on an integrated procedure for the construction of the distribution of aggregate losses, using internal and external loss data. It is illustrated on a 2x2 matrix of two selected business lines and two event types, drawn from a database of 3000 losses obtained from a large European banking institution. For each cell, the method calibrates three truncated distributions functions for the body of internal data, the tail of internal data, and external data. When the dependence structure between aggregate losses and the non-linear adjustment of external data are explicitly taken into account, the regulatory capital computed with the AMA method proves to be substantially lower than with less sophisticated approaches allowed by the Basel II Accord, although the effect is not uniform for all business lines and event types. In a second phase, our models are used to estimate the effects of operational risk management actions on bank profitability, through a measure of RAROC adapted to operational risk. The results suggest that substantial savings can be achieved through active management techniques, although the estimated effect of a reduction of the number, frequency or severity of operational losses crucially depends on the calibration of the aggregate loss distributions.

Measuring and Managing Operational Risk in the Financial Sector: An Integrated Framework

This paper proposes a methodology to analyze the implications of the Advanced Measurement Approach (AMA) put forward by the Basel II Accord for the assessment of operational risk. We develop an integrated procedure for the construction of the distribution of aggregate losses, using internal and external data. It is illustrated on a 2x2 matrix of two selected business lines and two event types, drawn from a database of 3000 losses obtained from a large European banking institution. For each cell, the method calibrates three truncated distributions functions for the body of internal data, the tail of internal data, and external data. When the dependence structure between aggregate losses and the non-linear adjustment of external data are explicitly taken into account, the regulatory capital computed with the AMA method is substantially lower than with less sophisticated approaches, although the effect is not uniform. We then estimate the effects of operational risk management actions on bank profitability, through a measure of RAROC adapted to operational risk. The results suggest that substantial savings can be achieved through active management techniques, although the effect of a reduction of the frequency or severity of operational losses depends on the calibration of the aggregate loss distributions.