Loss Distribution Approach to Operational Risk: Analysis Template for Spotfire 1.0

Overview

Financial institutions incur various operational risk events.

For example, the Basel II regulations identify the following event types: Internal Fraud; External Fraud; Employment Practices and Workplace Safety; Clients, Products, & Business Practice; Damage to Physical Assets; Business Disruption & Systems Failures; Execution, Delivery, & Process Management. The firm will use a combination of historical internal data, and relevant industry data to construct distributions of both frequency and severity of different types of operational risk events in its different lines of business.

Using these distributions, the firm can simulate the losses in each cell of the event type / line of business matrix in a given risk horizon, such as one year. Driven by either regulatory or strategic reasons, the firm will demonstrate reserves up to the specified percentile of loss in its annual loss distribution. This amount is called Value-at-Risk for the given risk horizon ("annual") and percentile rank ("99th").

Loss Distribution Approach to Operational Risk - Analysis Template for Spotfire - details

Application Type:  Analysis template.  The .dxp template in this distribution is intended to be used as a stand-alone solution to perform the analysis described below. 

Software: The .dxp file with embedded TERR data functions is the complete analysis template.  Open this file in Spotfire for complete instructions on how to use it.

Description:

Frequency-Severity Models

This analysis implements simple frequency-severity models for Operational Risk event types. This forms the basis of the Loss Distribution Approach alternative in the Basel regulations.

The user enjoys a seamless experience in an analysis that invokes both Data Functions and pure Spotfire transformations through controls on the page. The user can invoke either predetermined models, or run models specified on the fly.

Financial institutions incur various operational risk events. For example, the Basel II regulations identify the following event types:

1. Internal Fraud - misappropriation of assets, tax evasion, intentional mismarking of positions, bribery
2. External Fraud - theft of information, hacking damage, third-party theft and forgery
3. Employment Practices and Workplace Safety - discrimination, workers compensation, employee health and safety
4. Clients, Products, & Business Practice - market manipulation, antitrust, improper trade, product defects, fiduciary breaches, account churning
5. Damage to Physical Assets - natural disasters, terrorism, vandalism
6. Business Disruption & Systems Failures - utility disruptions, software failures, hardware failures
7. Execution, Delivery, & Process Management - data entry errors, accounting errors, failed mandatory reporting, negligent loss of client assets

The firm will use a combination of historical internal data, and relevant industry data to construct distributions of both frequency and severity of different types of operational risk events in its different lines of business. Using these distributions, the firm can simulate the losses in each cell of the event type / line of business matrix in a given risk horizon, such as one year.

Driven by either regulatory or strategic reasons, the firm will demonstrate reserves up to the specified percentile of loss in its annual loss distribution. This amount is called Value-at-Risk for the given risk horizon ("annual") and percentile rank ("99th").

source: Emphasis: Modern Operational Risk Management, Ali Samad-Khan, Towers Watson

The exhibit above illustrates the workflow involved in estimating the Total Loss Distribution of Operational Risk, using the LDA approach.

The amount up to Expected Loss (mean) is referred to as Provisions, and the remaining amount up to the Basel / Solvency standards is called Economic Capital. This analysis will generate a single cell of the Risk Matrix above. See the illustration below. Please download the template to try this out with your data.