 |
|
|
Moody's KMV Research |
|
|
|
|
|
|
|
|
|
 |
|
White Papers |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Contact Us |
|
|
|
Contact Us today to see why Moody's KMV is the right choice.
|
|
|
|
|
|
|
New Research | Portfolio Credit Risk | Portfolio Valuation | Model Validation & Testing |
|
Public Company Default Modeling Methodologies
Power and Level Validation of Moody’s KMV EDF™ Credit Measures in North America, Europe, and Asia
Douglas W. Dwyer & Irina Korablev, September 10, 2007
(PDF document ~ 763KB)
In this paper, we validate the performance of Moody’s KMV EDF™ credit measures in its timeliness of default prediction, ability to discriminate good firms from bad firms, and accuracy of levels in three regions: North America, Europe, and Asia. We focus on the period
1996–2006 for most of our tests. Wherever possible, we compare the performance to that of other popular alternatives, such as agency ratings, Moody’s KMV RiskCalc® EDF credit measures, Altman’s Z-Scores, and a simpler version of the Merton model. We find that EDF credit measures perform consistently well across different time horizons, and different subsamples based on firm size and credit quality. Our tests indicate that EDF credit measures provide a very useful measure of credit risk that can be applied throughout the world.
EDF™ 8.0 MODEL ENHANCEMENTS
Douglas W. Dwyer & Shisheng Qu, January, 2007
(PDF document ~ 341KB)
The Moody’s KMV Expected Default Frequency™ model of public firms is the pioneering implementation of a structural model that gives investors the ability to monitor credit risk across a broad range of firms. The release of the EDF™ 8.0 model represents a major recalibration of the model, which incorporates both a larger default dataset and improved estimation techniques that derive the EDF term structure from credit migration.
The EDF 8.0 model refines the mapping of the Distance-to-Default (DD) to the EDF level. The resulting EDF value is a superior measure of both absolute and relative risk. The EDF 8.0 model also provides improved granularity with a wider range of EDF credit measures so that fewer credits hit the model cap and floor.
These refinements meet the increased demands that market participants are placing on quantitative credit risk models. Market participants demand models that provide more granular measure of credit risk. They also want models they can use to determine the fair value spread on a given exposure. Models need to be transparent and validated. The validity of the EDF level needs to be demonstrated given its importance in computing both required economic and regulatory capital.
In this document, we describe the process of mapping the DD to an EDF credit measure. Further, we show the impact of the mapping changes on the EDF level, required economic capital, required regulatory capital, and the EDF Credit Categories, as well as the implications for the EDF-implied spreads for both Bonds and CDS contracts. Finally, we provide more details regarding the inner workings of the model.
Power and Level Validation of the EDF™ Credit Measure in the U.S. Market
Jeff Bohn, Navneet Arora, & Irina Korablev, March 18, 2005
(PDF document ~ 393KB)
The new Basel Capital Accord states that “The methodology for assigning credit assessments must be rigorous, systematic, and subject to some form of validation based on historical experience.” There are two important components to this validation process: the ability to predict defaults and the accuracy of the default predictive measure.
Modeling Default Risk
Peter Crosbie & Jeffrey R. Bohn, Revised December 18, 2003
(PDF document ~ 469KB)
Default risk is the uncertainty surrounding a firm's ability to service its debts and obligations. Prior to default, there is no way to discriminate unambiguously between firms that will default and those that won't. At best we can only make probabilistic assessments of the likelihood of default. As a result, firms generally pay a spread over the default-free rate of interest that is proportional to their default probability to compensate lenders for this uncertainty.
FINANCIAL EDF MEASURES A New Model of Dual Business Lines
Martha Sellers & Navneet Arora
(PDF document ~ 2MB)
Recent financial institution research at MKMV has focused on the implications of the fact that certain large banks and non-bank financial institutions behave as combinations of two quite different businesses: a financial asset portfolio and franchise or service business.
A Comment on Market vs. Accounting-Based Measures of Default Risk
John Andrew McQuown, September 1993
(PDF document ~ 404KB)
Lending requires resolution of two fundamental questions: (1) what is the likelihood of default; and (2) what will be lost if default occurs? The "probability of default" derives from the dynamic fortunes of the borrower corporation. Default occurs when the borrower's resources are depleted to such an extent that a promise to pay cannot be met. The "loss given default" depends, primarily, upon security and seniority. More generally, the facility agreement bears significantly on the prospects of loss should default occur. The loss given default expectation is, then, highly facility dependent. Although loss given default is an important source of uncertainty in lending, the dominant source of uncertainty, and thereby risk, is the default probability itself. This paper will focuses on measurement of the probability of default.
Back to Top
Private Company Default Modeling Methodologies
Examples of Overfitting Encountered When Building Private Firm Default Prediction Models
Douglas W. Dwyer, April 2005
(PDF document ~245KB)
The key to building default prediction models, if they are to be incorporated into credit risk management systems, is to build the most powerful model possible subject to the constraints that it is transparent, usable, and intuitive. In this process, we must constantly be on guard for whether or not we have overfit the data. In this paper, we present two examples of overfitting that we encountered while building private firm models. These issues, if not detected, would have reduced the usability of the model and overstated the true predictive power of the model in real credit decision-making.
Moody’s KMV RiskCalc™ V3.1 Model
Douglas W. Dwyer, Ahmet E. Kocagil, Roger M. Stein April 2004
(PDF document ~750KB)
This white paper outlines the methodology, performance, and key economic benefits of the Moody's KMV Expected Default Frequency™ (EDF™) RiskCalc™ model, which powers the next-generation of default prediction technology for middle market, private firms. With EDF RiskCalc v3.1, Moody's KMV answers an important challenge faced by our customers: "How can we support our decision-making process for extending loans, managing portfolios and pricing debt securities when there is little available market insight into a firm's prospects, as is the case for middle market credits.
Moody's RiskCalc™ for Private Companies: Korea
Introduction to Rating Methodology in Korean
Rating Methodology in Korean
Ahmet E. Kocagil & Alexander Reyngold, May 2003
(PDF document ~ 274KB)
In a continuing effort to provide benchmarks for private middle market companies, Moody’s KMV has built a model for estimating firm default probabilities for private Korean companies which utilizes local company financial statements.
Moody's RiskCalc™ for Private Companies: Nordic Region
Ahmet E. Kocagil, Nicole Seiberlich, Özveri Teymur, Angelina Grass, Edward Parillon, Phil Escott and Frank Glormann, April 2003
(PDF document ~ 290KB)
In recognition of the growing need for benchmarks in the rating of middle market companies, Moody’s KMV is creating models for estimating firm probabilities of default using financial statement data. RiskCalc for Nordic private companies has been designed and calibrated for use on private companies in Denmark, Finland, Norway and Sweden.
Systematic and Idiosyncratic Risk in Middle-Market Default Prediction: A Study of the Performance of the RiskCalc™ and PFM™ Models
Roger M. Stein, Ahmet E. Kocagil, Jeff Bohn & Jalal Akhavein, February 2003
(PDF document ~ 3.4MB)
Clients of Moody's KMV (legacy Moody’s Risk Management Services and legacy KMV) have often requested information on the relative performance of the legacy KMV Private Firm Model™ (PFM) and the legacy Moody's RMS RiskCalc™ models. Embedded within such requests is a desire to understand better the relative importance of the various drivers that each model uses to predict default.
Moody's Approach to Rating SME CLOs with RiskCalc Japan
Yusuke Seki, February 17, 2003
(PDF document ~ 384KB)
In 2002, Moody's Investors Service started using RiskCalc Japan for private companies in its ratings of CLOs backed by loans to small-and medium-size enterprises (SMEs). As of end-January 2003, Moody’s had used this analytical tool to rate 7 CLO deals, including 6 publicly rated transactions.
Moody's RiskCalc™ Model for Singaporean Private Firms
Ahmet E. Kocagil & Alexander Reyngold, October 2002
(PDF document ~ 633KB)
Self-contained description of the development and validation of the Moody’s RiskCalc™ model for Singaporean private companies. However, some details are omitted as a more detailed handling of some of the methodology is contained in RiskCalc™ for Private Companies: Moody’s Default Model and, RiskCalc for Private Companies: Australia documents.
Moody's RiskCalc™ Model for Austrian Private Firms
German Language Version
Ahmet E. Kocagil, Ralf Imming, Frank Glormann & Phil Escott, September 2002
(PDF document ~ 645KB)
Self-contained description of the development and validation of the first version of Moody's RiskCalc™ for Austrian private companies. However, some details are omitted as a more detailed handling of some of the methodology is contained in "RiskCalc™ for Private Companies: Moody's Default Model."
Moody's RiskCalc™ Model for Italian Private Firms
Ahmet E. Kocagil, Vishnu Vasudev, Frank Glormann & Phil Escott, September 2002
(PDF document ~ 328KB)
Self-contained description of the development and validation of the first version of the Moody’s RiskCalc™ for Italian private companies. However, some details are omitted as a more detailed handling of some of the methodology is contained in “RiskCalc™ for Private Companies: Moody’s Default Model."
Moody's RiskCalc™ Model for Portuguese Private Firms
Adrian Murphy, Ahmet E. Kocagil, Phil Escott & Frank Glormann, September 2002
(PDF document ~ 736KB)
Self-contained description of the development and validation of the first version of the Moody’s RiskCalc™ for Portuguese private companies. However, some details are omitted as a more detailed handling of some of the methodology is contained in "RiskCalc™ for Private Companies: Moody’s Default Model."
Moody's RiskCalc™ Model for Dutch Private Firms
Alex Altshuler, Ahmet E. Kocagil, Frank Glormann & Phil Escott, September 2002
(PDF document ~ 737KB)
Self-contained description of the development and validation of the first version of the Moody’s RiskCalc™ for Dutch private companies. However, some details are omitted as a more detailed handling of some of the methodology is contained in RiskCalc™ for Private Companies: Moody’s Default Model.
Moody's RiskCalc™ Model for Australian Private Firms: Version 1.5
Ahmet E. Kocagil, Douglas W. Dwyer & André Salaam, August 2002
(PDF document ~ 966KB)
Self-contained description of the development and validation of version 1.5 of Moody's RiskCalc™ for Austrian private companies. The previous version of RiskCalc™ model for private Australian companies was released at the end of 2000 as one of the first RiskCalc™ private firm default models. At the time of this writing, the new version of the Australian RiskCalc™ model joins RiskCalc™ private firm models for the US, Canada, Mexico, Japan, Germany, Spain, France, UK, Netherlands, Belgium, Portugal, as well as a US bank model. Each model in this suite is designed to allow users to attach probabilities of default to private firms throughout the world in a consistent manner and framework. This allows users to attach default probabilities to private firms and to rank them in terms of their default risk.
Moody's RiskCalc™ for Private US Banks Model
Ahmet E. Kocagil, Alexander Reyngold, Roger M. Stein & Eduardo Ibarra, July 2002
(PDF document ~ 641KB)
This report documents RiskCalc for U.S. Banks, Moody’s model for estimating the probability of default (PD) for privately-held U.S. banks, thrifts, and bank holding companies. RiskCalc for U.S. Banks is a robust and validated model that produces one- and five-year PDs. It predicts separate PDs for bank holding companies and bank and thrift subsidiaries.
Benchmarking Default Prediction Models: Pitfalls and Remedies in Model Validation
Roger M. Stein, July 2002
(PDF document ~ 583KB)
We discuss the components of validating credit default models with a focus on potential challenges to making inferences from validation under real-world conditions. We structure the discussion in terms of: (a) the quantities of interest that may be measured (calibration and power) and how they can result in misleading conclusions if not taken in context; (b) a methodology for measuring these quantities that is robust to non-stationarity both in terms of historical time periods and in terms of sample firm composition; and (c) techniques that aid in the interpretation of the results of such tests. The approaches we advocate provide means for controlling for and understanding sample selection and variability. These effects can in some cases be severe and we present some empirical examples that highlight instances where they are and can thus compromise conclusions drawn from validation tests.
Moody's RiskCalc™ for Belgian Private Firms
Dina Westenholz, Wolfgang Malzkorn, Ahmet Kocagil, Frank Glormann & Phil Escott, June 2002
(PDF document ~ 404KB)
Self-contained description of the development and validation of the first version of the RiskCalc™ for Belgium private companies. However, some details are omitted as a more detailed handling of some of the methodology is contained in RiskCalc™ for Private Companies: Moody’s Default Model.
Moody's RiskCalc™ for UK Private Firms
Ahmet E. Kocagil & Roger M. Stein, February 2002
(PDF document ~ 318KB)
Self-contained description of the development and validation of the first version of the RiskCalc™ for UK private companies. However, some details are omitted as a more detailed handling of some of the methodology is contained in RiskCalc™ for Private Companies: Moody’s Default Model.
Moody's RiskCalc™ for Private Companies - The Japanese Model
Ahmet E. Kocagil & Jalal D. Akhavein, December 2001
(PDF document ~ 325KB)
Self-contained description of the development and validation of the Japanese default model; however, some details are omitted. A more detailed handling of some of the methodology is contained in RiskCalc™ for Private Companies: Moody's Default Model and RiskCalc™ for Private Companies II.
Moody's RiskCalc™ for Private Companies - The French Model
French language version
Jens Bech, Phil Escott, Frank Glormann & Ahmet E. Kocagil, December 2001
(PDF document ~ 522KB)
In recognition of the growing need for benchmarks in the rating of middle market companies, Moody's is creating models for estimating firm probabilities of default using financial statement data. This model joins Moody’s RiskCalc™ models for private companies in Germany and Spain as the latest in a networks of European models that are being co-developed with Oliver Wyman & Company, the leading global strategy consulting firm dedicated to the financial services industry.
Moody's RiskCalc™ for Private Companies - The Mexican Model
Spanish language version
Ahmet E. Kocagil, Jalal D. Akhavein & Alexander Reyngold, December 2001
(PDF document ~ 352KB)
RiskCalc™ for Mexican private companies is the first and only quantitative credit assessment model available for evaluating middle market companies in Mexico.
Moody's RiskCalc™ for Private Companies - The Spanish Model
Spanish language version
Phil Escott, Ahmet E. Kocagil, Pedro Rapallo & Miguel Yague, July 2001
(PDF document ~ 500KB)
Self-contained description of the development and validation of the Spanish default model; however, some details are omitted. A more detailed handling of some of the methodology is contained in RiskCalc™ for Private Companies: Moody’s Default Model.
Moody's RiskCalc™ for Private Companies - The German Model
German language version
Phil Escott, Frank Glormann & Ahmet E. Kocagil, May 2001
(PDF document ~ 555KB)
Self-contained description of the development and validation of RiskCalc™ Germany; however, some details may be omitted. A more detailed handling of some of the methodology is contained in RiskCalc™ for Private Companies: Moody's Default Model (2000).
RiskCalc™ for Private Companies II: More Results and the Australian Model
Eric Falkenstein, Andrew Boral & Ahmet E. Kocagil, December 2000
(PDF document ~ 611KB)
Description of Moody's unique private firm database in Australia, with comparisons to the data on US and Canada. Also a description of the derivation and testing of Moody's default model, however, some nuances may be omitted. A more complete documentation of the approach is contained in RiskCalc™ For Private Companies: Moody's Default Model.
RiskCalc™ For Private Companies: Moody's Default Model
Eric Falkenstein, May 2000
(PDF document ~ 3.1MB)
This report describes and documents Moody's version of its RiskCalc™ default model for private firms. RiskCalc™ analyzes financial statement data to produce default probability predictions for corporate obligors - particularly those in the middle market. We discuss the model's derivation in detail, analyze its accuracy, and provide context for its application. The model's key advantage derives from Moody's unique and proprietary middle market private firm financial statement and default database (Credit Research Database), which comprises 28,104 companies and 1,604 defaults.
Back to Top
Loss Given Default Modeling Methodologies
LossCalc™ V2 : Dynamic Prediction of LGD
Greg M. Gupton & Roger M. Stein, January 2005
(PDF document ~ 1.13MB)
LossCalc is a statistical model that incorporates information at different levels: collateral, instrument, firm, industry, country, and the macroeconomy to predict LGD. It significantly improves on the use of historical recovery averages to predict LGD, helping institutions to better price and manage credit risk.
LossCalc™ : Moody's Model for Predicting Loss Given Default (LGD)
Greg M. Gupton & Roger M. Stein, February 2002
(PDF document ~ 1.2MB)
This report describes and documents LossCalc,Moody's model for predicting loss given default (LGD): the equivalent of (1 -recovery rate ). LGD is of natural interest to investors and lenders wishing to estimate future credit losses. LossCalc is a robust and validated model of United States LGD for bonds, loans, and preferred stock. It produces estimates of LGD for defaults occurring immediately and for defaults occurring in one year. These two point-in-time estimates can be used to predict LGD over holding periods.
Back to Top
Default and Transition Studies for Moody's Rated Issuers
Corporate Defaults Refuse to Yield in 2002
July 2002
Default & Recovery Rate of European Corporate Bond Issuers
July 2002
1Q2002 Default Commentary
May 2002
Default & Recovery Rate of Corporate Bond Issuers
February 2002
Data from the exhibit
Argentinean Capital Controls Likely to Boost 2002 Global Default Rate - January 2002
3Q2001 Default Commentary
Oct 2001
2Q2001 Default Commentary
July 2001
Default and Recovery Rates of Convertible Bond Issuers: 1970 - 2000
July 2001
Critical Issues in Evaluating the Creditworthiness Of Convertible Debt Securities
July 2001
1Q2001 Default Commentary
April 2001
Testing For Rating Consistency In Annual Default Rates
February 2001
Default and Recovery Rates of Corporate Bond Issuers: 2000 - February 2001
2000 Public Corporate Bond Defaults
Data from the exhibit
3Q2000 Default Commentary
October 2000
Moody's Approach to Evaluating Distressed Exchanges
July 2000
2Q2000 Default Commentary
July 2000
Default Forecast Commentary
May 2000
1Q2000 Default Commentary
April 2000
Historical Default Rates of Corporate Bond Issuers, 1920-1999
January 2000
Historical Default Rates of Corporate Bond Issuers, 1920-1998
January 1999
Historical Default Rates of Corporate Bond Issuers, 1920-1997
February 1998
Historical Default Rates of Corporate Bond Issuers, 1920-1996
January 1997
Corporate Bond Defaults and Default Rates, 1938-1995
January 1996
Corporate Bond Defaults and Default Rates, 1970-1994
January 1995
Corporate Bond Defaults and Default Rates, 1970-1993
January 1994
Corporate Bond Defaults and Default Rates, 1970-1992
January 1993
An Historical Analysis of Moody's Watchlist
October 1998
Commercial Paper Defaults and Rating Transitions, 1972-2000
October 2000
Commercial Paper Defaults and Rating Transitions, 1972-1998
May 1998
Commercial Paper Defaults and Rating Transitions, 1972-1995
December 1995
Moody's Rating Migration and Credit Quality Correlation, 1920-1996
July 1997
Credit Shifts in Residential Mortgage Pass-Through Securities: A Rating Transition Study Update
May 1996
How and Why Do Structured Finance Ratings Change? Rating Transition Study for Single-Family Residential Mortgage Pass-Through Securities
May 1995
Commercial Paper Defaults 1970-1993
October 1994
Measuring Changes in Corporate Credit Quality
November 1993
Back to Top
Recovery Studies for Moody's Rated Issuers
Default & Recovery Rate of European Corporate Bond Issuers
July 2002 (PDF 146KB)
Bank Loan Loss Given Default
November 2000 (PDF 179KB)
Debt Recoveries for Corporate Bankruptcies
June 1999 (PDF 196KB)
Bankrupt Bank Loan Recoveries
June 1998 (PDF 206KB)
Defaulted Bank Loan Recoveries
November 1996(PDF 82KB)
Back to Top
Qualitative Risk Assessment
Assessing a Knowledge-based Approach to Commercial Loan Underwriting
Research Report #2-00-1
(PDF 354KB)
Back to Top |
|
|
|
