Portfolio Modeling

Our models accurately calculate stand-alone risk and return measures of instruments in a portfolio, as well as portfolio-referent risk of those instruments. Our models combine these measures to deliver an extensive set of economic performance metrics, including portfolio return, expected loss, unexpected loss, economic capital, and expected shortfall. Our portfolio framework supports a wide range of credit investments and contingencies, including bonds, equities, term loans, revolving credit lines, credit derivatives, and structured instruments.

This paper develops a method to back-allocate to individual positions the market risk capital requirement that a bank must satisfy under the revised standardized approach proposed by the Basel Committee. Our method assesses the contribution of single positions or sub-portfolios to the overall capital charge. One important feature of our method is that it provides insight on which positions, sub-portfolios, and risk factors drive the capital charge and which help mitigate it. A negative contribution indicates that a marginal increase in the position would lead to a decrease in the capital charge, and vice versa.

Authors: Lorenzo Boldrini, Tiago Pinheiro
Date: April 2017
Download PDF
IFRS 9 materially changes how institutions set aside loss allowance. With allowances flowing into earnings, the new rules can have dramatic effects on earnings volatility. In this paper, we propose general methodologies to measure and manage credit risk in the earnings of a loan portfolio under IFRS 9. We walk through IFRS 9 rules and the different mechanisms that it interacts with which flow into earnings dynamics. We demonstrate that earnings will be impacted significantly by credit migration under IFRS 9. In addition, the increased sensitivity to migration will be further compounded by the impact of correlation and concentration. We propose a modeling framework that measures portfolio credit earnings volatility and discuss several metrics that can be used to better manage credit risk in earnings.

Authors: Amnon Levy, Xuan Liang, Yanping Pan, Yashan Wang, Pierre Xu, Jing Zhang
Date: March 2017
Download PDF
The credit portfolio framework developed by Moody’s Analytics accounts for links between default risk and recovery risk. We refer to these links as PD-LGD correlations. Using appropriate values of parameters that define PD-LGD correlations is an important prerequisite for a portfolio analysis. We present GCorr 2016 LGD model, which provides estimates of these parameters.

GCorr 2016 LGD leverages similar methodology for estimating parameters as the previous version of the PD-LGD correlation model, with some modifications required due to the nature of new data. While the previous version of the PD-LGD correlation model employed data provided by Moody’s Analytics LossCalc2.0 model, GCorr 2016 LGD utilizes LossCalc4.0 output data as well as the default-recovery database (DRD). In addition to differing data sources, GCorr 2016 LGD incorporates more recent data than the previous model, including the effects of the financial crisis of 2008-2009.

Webinar Highlights:
Empirical patterns in recovery dynamics over recent periods
New estimation of parameters describing link between defaults and recoveries
Impact of the new parameters on portfolio risk metrics.

Presenters: Yiting Xu, Noelle Hong
Date: February 2017
watch now
Modeling new origination is important for forecasting the future dynamics of a portfolio, and it is becoming prevalent for banks to use these models for capital and risk management, stress testing, and strategic planning. In recent years regulators have laid out stress testing frameworks that focus on modeling the relationship between new origination and the macro environment. The main challenge with modeling new origination is finding data on new origination dynamics over time.

In this webinar we propose using the Loan Accounting System data extracted from Moody’s Analytics Credit Research Database to construct and examine new origination dynamics of C&I loans to middle-market borrowers over time, and highlight the different patterns that emerge for different portfolio segments. Our analysis shows how important different types of segmentation are for understanding new origination dynamics.

Authors: Tomer Yahalom
Date: October 18, 2016
watch now
When parameterizing an Economic Capital (EC) framework, organizations must consider how losses and gains on principal and coupons/fees are recognized, if they are to ensure appropriate capitalization. The level of loss allowance and capital organizations hold must be sufficient to cover potential losses.

Mark Wells, Associate Director of Portfolio Research at Moody’s Analytics, outlines how the parameterization of an Economic Capital model differs for accrual and securities portfolios and relates the parameterization approaches with those associated with Basel Advanced-IRB calculations.

Presenter: Mark Wells
Date: October 2016
watch now

Financial institutions are seeking ways to gain a better understanding of their credit portfolios’ risk dynamics, allowing them to foresee and to prepare for potential increases in capital requirements resulting from economic shocks.

Aubrey Clayton, Associate Director, and Xuan Liang, Assistant Director of Portfolio Research at Moody’s Analytics, will discuss how to leverage a multi-period capital planning framework to determine the appropriate capital buffer level for a portfolio under various economic scenarios and how to fortify capital buffers through portfolio selection across periods of macroeconomic stress.

Webinar Highlights:
Overview of Multi-Period Capital Analysis
Brute Force Approach
Proxy Function Approach

Presenters: Aubrey Clayton, Xuan Liang
Date: October 2016

watch now
Many financial institutions prefer to take longer-term views when assessing the risks of their credit portfolio. While forward-looking or Point-in-Time (PIT) parameters might be more reflective of the current economic environment, frequent updates may create fluctuations in risk measures, such as economic capital and unexpected loss, which may not be desirable in some applications.

Jimmy Huang, Associate Director of Portfolio Research at Moody’s Analytics will discuss two approaches that financial institutions can consider to estimate Through-the-Cycle (TTC) correlation parameters.

Presenter: Jimmy Huang
Date: October 11, 2016
watch now
This paper presents a novel modeling approach that allows for better management of the interplay between supply and demand dynamics for regulatory capital, combining an economic framework with regulatory capital and new loss recognition rules. The framework is particularly relevant in understanding the extent to which IFRS 9 can lead to more aggressive provisioning, which feeds into earnings volatility. Our approach provides guidance on how organizations can better manage their capital buffer, considering investment concentration, its impact on earnings volatility, and the relationship with regulatory capital requirements. Imperative to portfolio management, the framework recognizes the likelihood of a capital shortfall being significantly impacted by portfolio asset class, geography, industry, and name concentration, as extreme fluctuations in capital supply and demand occur more often for institutions holding more concentrated portfolios. Finally, we discuss integrated investment and strategic decision measures that account for the full spectrum of economic risks and interactions with regulatory and accounting rules, as well as instruments’ contribution to earnings volatility and capital surplus dynamics.

Authors: Amnon Levy, Andriy Protsyk, Pierre Xu, Jing Zhang
Date: September 29, 2016
Download PDF
Under loss recognition rules specified by IFRS 9, credit deterioration can lead to more aggressive loss allowance (reducing regulatory capital (RegC) supply as available equity is written off), higher risk weighted assets and higher demand for RegC. Leveraging an EC framework allows institutions to account for such concentration and diversification effects on RegC requirements and helps institutions make better investment decisions.

Amnon Levy, Managing Director of Portfolio Research at Moody’s Analytics,discusses a novel modeling approach that allows organizations to better manage the supply and demand dynamics for regulatory capital. The approach marries an economic capital (EC) framework with (RegC) and loss accounting rules.

Presenter: Dr. Amnon Levy
Date: August 2016
watch now
Prudent risk management needs to account for both the regulatory capital requirement faced by the institution and the intrinsic risk of the portfolio. The Composite Capital Measure helps risk managers to allocate capital and make investment decisions accordingly.

Pierre Xu provides an overview to the Composite Capital Measure. He discusses how the measure should be parameterized to reflect the degree to which an institution is constrained by regulatory capital requirements and examine the dynamics and investment implications of the measure under different economic scenarios.

Presenter: Pierre Xu
Date: August 2016
watch now
Banks commonly use Risk Contribution, or contribution to portfolio Unexpected Loss (i.e., standard deviation), as a risk allocation method. While the method has some very desirable properties, it can also produce seemingly counterintuitive dynamics, whereby high interest income-producing assets are associated with higher risk, all else being equal. This dynamic manifests from the higher interest income assets possessing higher value, leading to higher standard deviation in absolute terms. In reality, financial institutions often use interest income to offset losses, and thus, associate higher interest with lower risk. This paper introduces a new, income-adjusted form of Risk Contribution-based capital allocation, designed so that interest income offsets losses. The measure demonstrates improved properties for exposures with particularly high coupons.

Authors: Mark Wells, Andrew Kaplin, Amnon Levy
Date: August 31, 2016
Download PDF
Higher capital standards imposed by new stress testing requirements have forced organizations to address how to better manage capital to meet regulatory constraints. While maintaining higher capital levels is indeed mandatory, simply satisfying the requirement does not necessarily align with stakeholders’ preferences for optimal capital deployment and investment decisions. CCAR-style stress tests are requirements that organizations must adhere to; however, these exercises likely do not reflect how stakeholders actually trade off risk and return.

Required economic capital (EC) accounts for economic risks such as diversification and concentration effects. When used in measures such as return on risk-adjusted capital (RORAC), EC can provide useful insights that allow institutions to optimize risk-return profiles and to facilitate strategic planning and limit setting, as well as quantify risk appetite.

Authors: Pierre Xu, Amnon Levy
Date: May 5, 2016
Download PDF
This paper proposes and illustrates a multi-period capital planning framework that can be used to calculate a portfolio’s capital requirement over time and to determine the appropriate capital buffer level under various economic scenarios. Such analysis can help financial institutions gain a better understanding of credit portfolios’ risk dynamics, allowing them to foresee and to prepare for potential increases in capital requirements resulting from economic shocks.

Using Moody’s Analytics Stressed EL Calculator and RiskFrontier™, we implement the capital planning framework and analyze the impact of the 2015 CCAR scenarios on the capital requirement and capital buffer behaviors of a credit portfolio consisting of all U.S. public firms in CreditEdge™. Results show that capital buffer behaviors vary significantly under different scenarios and for various asset classes. We also observe that a proportion of the capital allocated to financial firms is always greater than their value proportion, and it increases for most periods under the Adverse and Severely Adverse Scenarios. This finding suggests that decreasing exposures in financial counterparties is more effective in terms of lowering the capital requirement when the economy undergoes stress.

Authors: Andy Kaplin, Xuan Liang
Date: April 21, 2016
Download PDF
This paper introduces a framework for stress testing portfolios of credit risk sensitive securities. Specifically, the framework uses a macroeconomic scenario to project stressed expected losses (EL) on the securities by accounting for credit quality changes, recovery risk effects, fluctuations in market price of risk, and interest rates paths. The calculations are carried out analytically over multiple periods.

Authors: Jay Harvey, Sunny Kanugo, Vishal Mangla, Libor Pospisil, Yashan Wang, Ian Ward, Kevin Yang
Date: April 20, 2016
Download PDF
This document presents a credit portfolio stress testing method that analytically determines multi-period expected losses under various macroeconomic scenarios. The methodology utilizes Moody’s Analytics Global Correlation Model (GCorr®) Macro model within the credit portfolio modeling framework. GCorr Macro links the systematic credit factors from GCorr to observable macroeconomic variables. We describe the stress testing calculations and estimation of GCorr Macro parameters and present several validation exercises for portfolios from various regions of the world and of various asset classes.

Authors: Noelle Hong, Jimmy Huang, Albert Lee, Amnon Levy, Marc Mitrovic, Olcay Ozkanoglu, Libor Pospisil
Date: April 20, 2016
Download PDF

When parameterizing an Economic Capital (EC) framework, organizations must consider how losses and gains on principal and coupons/fees are recognized, if they are to ensure appropriate capitalization. The level of loss allowance and capital organizations hold must be sufficient to cover potential losses. This paper outlines how parametrization differs for accrual and securities portfolios. In addition, we relate parametrization approaches with those associated with Basel Advanced-IRB calculations. We conclude that, when measuring an organization’s required economic capital buffer, the relevant loss reference point is the accounting value net of loss allowance — losses should be measured in excess of total spread. While seemingly inconsistent with the Basel A-IRB formulation, where losses are measured in excess of expected loss, the difference can be interpreted as loss allowance exactly aligning with expected loss.
 
Authors: Peter Bozsoki, Amnon Levy, Thomas Tosstorff, Mark Wells
Date: March 7, 2016

In some instances, financial institutions prefer to take longer-term views when assessing the risks of their credit portfolio. While forward-looking or Point-in-Time (PIT) parameters might be more reflective of the current economic environment, their frequent updates may create fluctuations in risk measures, such as economic capital and unexpected loss, which may not be desirable in some applications. This paper outlines two approaches that financial institutions can consider to estimate Through-the-Cycle (TTC) correlation parameters. The first approach averages PIT measures across years to obtain a longer-term TTC average. The second approach calibrates a TTC correlation measure that generates a default distribution in-line with the institution’s actual default distribution.

Presenter: Jimmy Huang, Dr. Amnon Levy, Libor Pospisil, Noelle Hong, Devansh Kumar Srivastava
Date: January 26, 2016

EDF metrics, provided by the Moody’s Analytics Public Firm Expected Default Frequency (EDF™) model, are forward-looking probabilities of default for public firms. The recently introduced EDF9 model, the 9th generation, incorporates insights attained by evaluating the behavior of the prior versions, over the course of the recent financial and sovereign debt crises. EDF9 utilizes a larger dataset, given the global expansion of the equity markets, enhanced data quality, and improvements in computational performance.

This paper investigates the impact of using EDF9 instead of EDF8 values as inputs for estimating credit portfolio risk measures within Moodys Analytics RiskFrontier®. The recent EDF9 enhancements affect portfolio risk analysis via various channels — due not only to new values for default probabilities, but also because the market Sharpe ratio (i.e. market-level risk premium) and asset return-based correlations for corporate exposures depend on time series of EDF measures. In this paper, we focus on the question of how using the new EDF9 default probabilities alter patterns in portfolio risk measures.

Authors: Noelle Hong, Jimmy Huang, Albert Lee, Marc Mitrovic, Tiago Pinheiro, Libor Pospisil, Andriy Protsyk, Yashan Wang
Date: December 2015
Download PDF

In this webinar, Moody's Analytics provides an overview of a number of approaches and best practices for setting risk- and macro scenario-based limits to quantify a risk appetite statement.

Presenter: Dr. Amnon Levy
Date: November 3, 2015 

watch now

The degree to which an organization’s regulatory capital is constraining impacts an investment’s appeal. The more constraint on the organization, the more heavily an instrument’s regulatory capital weighs down the investment’s appeal, with investments assigned higher regulatory capital impacted more. This paper explores a method for measuring the extent to which an organization’s regulatory capital binds and calibrates the model introduced by Levy, Kaplin, Meng, and Zhang (2012), which unifies regulatory and economic capital in investment decisions. We then examine the impact of the regulatory capital requirement on investment decisions based on the calibrated model. We find that the rank order of exposures’ risk-return tradeoff in our sample portfolio changes substantially when taking into account the regulatory capital constraint.

Authors: Pierre Xu, Amnon Levy, Qiang Meng, Andrew Kaplin
Date: August 4, 2015 

Download PDF

In this paper, we propose a composite capital allocation measure integrating regulatory and economic capital, based on the model introduced by Levy, Kaplin, Meng, and Zhang (2012). We show that our measure has ideal properties of an integrated capital measure. It specifies the capitalization rate needed to achieve the desired deleverage ratio — when the regulatory capital constraint is binding, composite capital for the overall portfolio aggregates to an institution’s top-of-the-house target capitalization rate. Our measure also redistributes required capital across instruments to account for instrument heterogeneities in both economic capital and the impact of regulatory requirements and, thus, has a natural application toward capital allocation. We find this measure is significantly higher than economic capital for instruments with high credit quality, reflecting the fact that the regulatory capital requirement is relatively more onerous for these instruments.

Authors: Pierre Xu, Amnon Levy
Date: August 6, 2015 

Download PDF

In this webinar, Moody’s Analytics will discuss practical considerations when unifying regulatory and economic capital in investment decisions and the method for measuring this unified approach. Since the financial crisis, regulations have forced financial institutions to adhere to increasing capital standards. New stress testing requirements and the advent of Basel III have raised the need for better capital management. A central problem faced by institutions today is to understand how to incorporate the impact of regulatory capital requirements into traditional economic capital-styled risk management.

Presenter: Amnon Levy
Date: July 21, 2015 

watch now

Moody’s Analytics GCorr™ Corporate model provides asset correlations of corporate borrowers for credit portfolio analysis. The GCorr Corporate model is based on 49 country factors. This paper introduces a new model, GCorr Emerging Markets, designed with more than 200 country-factors including emerging markets worldwide. The methodology expands GCorr Corporate’s 49 country factors to 200+ factors, each representing individual countries to better measure country concentration and diversification effects. The expanded factors cover predominately emerging market countries where we lack firm-level asset return data. For this reason, we refer to the extension as the GCorr Emerging Markets model. This model allows financial institutions with commercial exposures to smaller and emerging countries to better describe correlations across these countries, as well as to better capture diversification effects when investing in a wide cross-section of these countries. 

Authors: 
Jimmy Huang, Libor Pospisil, Noelle Hong
Date: July 13, 2015

Download PDF

This document details the analysis we perform to better understand SMEs’ credit quality dynamics and to quantify the differences in credit migration between SMEs and public firms. We estimate a set of transition matrices for SMEs based on Moody’s Analytics Credit Research Database (CRD™), a comprehensive dataset containing loan and accounting information for a large sample of SME borrowers. We then validate these transition matrices to show their stability across different sizes and industry segments, as well as across geographies. Our analytical comparison of transition matrices highlights similarities in migration dynamics across different SME segments. 

Authors: 
Peter Bozsoki, Sunny Kanugo, Yashan Wang

Date: June 18, 2015
Download PDF

This document presents validation results for the credit-interest lattice or the multi-dimensional lattice (MDL) valuation model within Moody’s Analytics RiskFrontier™. We focus on valuations of a large sample of corporate bonds, January 2006 – July 2013. We also produce valuations using the credit-only lattice and compare performance of the two lattice models. We find that model valuations compare extremely well with market transaction prices. Further, the MDL model produces better valuations for high credit quality bonds, especially in higher interest rate regimes. These findings validate the model’s ability to accurately value risky assets while accounting for both credit and interest rate risks.  We also compare the bottom-up approach for risk integration implemented in the joint lattice model with a traditional top-down approach. 

Authors: Sunny Kanugo, Yanping Pan, Rama Sankisa, Yashan Wang 
Date: June 18, 2015

Download PDF
In this paper, we explore leveraging an organization’s economic capital framework to quantify the Risk Appetite Statement (RAS) via risk- and macro scenario-based limits. Risk-based limits create a level playing field, using risk-based metrics to align with the organization’s risk appetite. Macro scenario-based limits control exposures to adverse macroeconomic scenarios and are frequently viewed as more intuitive and more tangible than risk-based limits. We also describe a number of approaches for setting risk- and macro scenario-based limits: top of- the-house (TOTH) risk limits, standalone sub-portfolio (SASP) risk limits, portfolio referent sub-portfolio (PRSP) risk limits, as well as Stressed Expect Loss (SEL) Limits, and macro risk-based limits. 

Authors: Andrew Kaplin, Amnon Levy, Qiang Meng, Libor Pospisil 
Date: June 18, 2015
Download PDF
This paper investigates the impact of using EDF9 instead of EDF8 values as inputs for estimating credit portfolio risk measures within Moody's Analytics RiskFrontier®. The recent EDF9 enhancements affect portfolio risk analysis via various channels — due not only to new values for default probabilities, but also because the market Sharpe ratio (i.e. market-level risk premium) and asset return-based correlations for corporate exposures depend on time series of EDF measures. In this paper, we focus on the question of how using the new EDF9 default probabilities alter patterns in portfolio risk measures.

Authors: Noelle Hong, Jimmy Huang, Albert Lee, Marc Mitrovic, Libor Pospisil
Date: June 15, 2015
Download PDF

In this webinar, Moody’s Analytics will discuss risk-based limits and macro scenario-based limits, both of which can be used to quantify a risk appetite statement. The risk appetite statement of an institution specifies the aggregate level and types of risks the institution is willing to take or avoid in order to achieve its business goals. The translation of risk appetite into limits allows an organization to achieve its strategic objectives and business plan while adhering to its risk capacity.

Presenter: Amnon Levy
Date: June 5, 2015 

watch now
This document describes the bottom-up joint interest rate and credit model in the Moody’s Analytics RiskFrontier™ application, with an emphasis on the estimation of two sets of parameters. The first set contains parameters of the Hull-White model, which specifies stochastic movements in interest rates over time. The second set includes correlation of interest rates and systematic credit risk factors in GCorr®, a multi-factor model for credit correlation.

Authors: Qiang Meng, Yanping Pan, Nihil Patel, Libor Pospisil, Yashan Wang, Kevin Yang
Date: December 23, 2013
Download PDF
During this webinar you will learn about Moody's Analytics Portfolio Research methodology and findings of the new unified measures (RORAC and EVA™) which allow institutions to rank-order their portfolios and potential deals in a way that accounts for both economic risks and regulatory changes.

Webinar Highlights:
Explore the different roles regulatory capital and economic capital play in credit portfolio managementReceive an introduction to the unified measures that incorporate both regulatory and economic capital Gain insight into the impact of accounting for regulatory capital
Presenter: Amnon Levy
Date: August 12, 2013
watch now
Print