Measuring & Managing Credit Risk: Understanding the EDF Credit Measure for Public Firms 2004.

Measuring & Managing Credit Risk:Understanding the EDF™ Credit Measure for Public Firms

2004

Measuring & Managing Credit Risk: Understanding the EDF™ Credit Measure for Public Firms

COPYRIGHT © 2004 MOODY’S KMV COMPANY. ALL RIGHTS RESERVED. WWW.MOODYSKMV.COM

2

1: THE CRITICAL ISSUE IN CREDIT

2: CALCULATING THE EDF CREDIT MEASURE

3: TESTING THE EDF CREDIT MEASURE

AGENDA



3

1 THE CRITICAL ISSUE IN CREDITSECTION



4

The Critical Issue in Credit

• The critical element in successfully managing a credit risk portfolio is that you must manage the dynamics of credit risk

• Why? A handful of names whose risk has changed explains most of the risk in credit portfolios



5

A Handful of Names Drive Most of the Risk

Managing outliers is important because a relatively small segment that disproportionately drive risk – most of the portfolio requires very little attention



6

Objectives in Modeling Default Risk

• Measure credit risk in terms of default probabilities rather than ordinal rankings

• Provide the most accurate forward-looking, causal model

• Provide frequent updates and early warning of changes in credit quality



7

Validation

Moody’s KMV EDF credit measures

• Have been tested on over 29 years of data representing over 4,000 defaults in the United States alone, as well as on smaller samples in various countries around the globe

• Outperform internal and agency ratings, simple Merton models and statistical scoring models in anticipating credit events and default



8

EDFs Predict Future Default Rates

0.09% 0.07% 0.42% 0.44%

1.25% 1.05%

3.82% 3.57%

15.21%

16.63%

0.00%

2.00%

4.00%

6.00%

8.00%

10.00%

12.00%

14.00%

16.00%

18.00%

.02%-.20% .21%-.70% .71%-2.0% 2.01%-7.0% 7.01%-20%

Predicted and Actual Default RatesCohorts Reformed

EDF (Predicted)

Observed Default History



9

The EDF Credit Measure

• EDF means Expected Default Frequency—the probability that a firm will default within a given time horizon

• We provide EDF term structures out to 5 years

• EDF Ranges from 2 to 2000 basis points



10

The EDF Credit Measure

• A company with a current EDF credit measure of 2% has a 2% probability of defaulting within the next twelve months. If we create a portfolio of 1000 such companies, on average, 20 default over the next year, and 980 do not.

• A company with a 2% EDF credit measure is 10 times more likely to default than a firm with a 0.20% EDF credit measure.



11

2 CALCULATING THE EDF CREDIT MEASURE

Expected Default Frequency for firms with publicly traded equity

SECTION



12

Drivers to the EDF Credit Measure

• Leverage– Market Value of Assets

vs.– Book Value of Liabilities

• Risk– Volatility of Asset Value



13

Leverage

Market Value

of Assets

Default Point

(Liabilities Due)

DefaultedNovember 2001



14

The Market Value of Assets

• The market value of the business, reflecting the equity market’s expectations of future cash flows

• Not directly observable—implied from the market value of equity and the book liabilities using option pricing theory

• Reflects deterioration & improvement before book assets or earnings

• Market values are dynamic and forward looking; they are the source of the model’s predictive power



15

Calculating Market Value of Assets

• Equity derives its value from the cash flows of the firm.• Equity is a call option on the firm’s assets: the right,

but not the obligation, to “buy” the firm’s assets from the lender by re-paying the debt.

Standard Options Terms

Call Option Value

Strike Price

Implied Underlying Asset Value

KMV Approach (Vasicek/Kealhofer Model)

= Market Value of Equity

= Book Liabilities

Implies Market Value of Assets

For more quantitative detail, please see the Moody’s KMV paper Modeling Default Risk.



16

Using Options Framework to Solve for Market Value of Assets

Option Value

Underlying Asset Value

0

When we know the Asset Value, and the Strike Price

We can calculate the implied option value

Strike Price



17

Using Options Framework to Solve for Market Value of Assets

Equity Value (Option Value)

0

And Calculate theImplied Asset Value

For public firms, we can observe the “option value” and the strike price

Underlying Asset Value

Liabilities Due



18

The Default Point

• A measure of the liabilities due in the event the firm is in distress

• Non-cash and long-term obligations put less financial stress on the firm

• Firms often increase leverage as they deteriorate

• The Default Point captures the point where the typical firm defaults



19

Default Point: An Example

Defaulted

Market Value of Assets

Default Point

Total Liabilities



20

Asset Volatility: A Measure of Business Risk

• The uncertainty around the market value of the business

• Reflects the degree of difficulty in forecasting the future cash flows

• Quantifies business risk: larger firms in the same industry tend to have lower volatility

• Computed by “de-levering” Equity Volatility



21

Asset Volatility: A Critical Driver

Time

Rising Equity Market Cap

Because of rising Asset Volatility

But a Dramatically Higher EDF



22

Putting It All Together

1 Yr

Distribution of asset value at horizon

AssetValue

Today

EDF

Time

Value

Default PointDistance-to-Default =3 Standard deviations

Asset Volatility(1 Std Dev)



23

How do we move from Distance to Default to a probability?



24

• We cannot use a statistics textbook.

• The probability from the Normal distribution is too low.

• Credit risk isn’t normal!• Statistics books don’t go

beyond 3.49—we see firms that are 4-6 standard deviations from default subsequently defaulting.



25

From Distance-to-Default to EDF

• Moody’s KMV uses actual default rates for companies in similar risk ranges to determine a functional relationship

• Requires a large database of actual defaults



26

Moody’s KMV Public Company Default Database 1973–2001

0

10

20

30

40

50

60

70

80

90

Nu

mb

er

of

De

fau

lts

• Over 29 years of data• Over 4,900 defaults• Over 400,000 company-years



27

Scaling DD to EDF

Form a “bucket of similar DD companies 1/1/1978

4.8 4.8

4.9 4.95 5.0

5.1 5.1 5.2

4.8 4.8 4.8

4.9 4.95 5.0

5.1 5.1 5.2

4.8 4.8 4.8

4.9 4.95 5.0

5.1 5.1 5.2

4.8

1 year later, how many have defaulted? 2 years later...

• Repeat the exercise for all ranges of DD

• Measure forward default observations for periods from 1 year to 5 years

• Form new buckets every year through the present and repeat steps



28

Scaling DD to EDF Credit Measures

Distanceto Default

ExpectedDefaultFrequency

EDF 43 bp

DD 4s



29

Summary: Measuring EDF

• Estimate asset value and asset volatility– Equity is a call option on asset value– Solve for implied asset value and volatility

• Calculate Distance to Default– Contractual obligations determine Default Point– Number of standard deviations from default

• Scale Distance to Default to EDF– Assign EDF using actual historical default rates



30

EDF Credit Measures

• We have been working on developing EDF credit measures and helping lenders and investors on real credit portfolios since 1989.

• We are on about the 5th generation of the Vasicek-Kealhofer EDF model.

• Experience pays off—we provide the most accurate and timely assessment of credit and default risk.



31

3 TESTING THE EDF CREDIT MEASURESECTION



32

EDF Credit Measure ResultsCan Market Information Improve Ratings?

• Moody’s KMV uses equity market information to determine a firm’s probability of default: the EDF credit measure.

• Here we sort the Non-Financial Single B firms on 12/31/92 by their EDF, as shown on the next slide.



33

103 B-Rated Firms as of 12/31/92

EDF Range

Number

of Firms

EDF Range High RiskLow Risk

0

2

4

6

8

10

12

14

0.15-0.65

0.67-1.14

1.15-2.04

2.16-2.63

2.69-3.33

3.69-5.32

5.64-8.49

8.84-20.00



34

Defaults 6 Months Later

EDF Range

Number

of Firms


0

2

4

6

8

10

12

14

0.15-0.65

0.67-1.14

1.15-2.04

2.16-2.63

2.69-3.33

3.69-5.32

5.64-8.49

8.84-20.00



35

Defaults 1 Year Later

EDF Range

Number

of Firms


0

2

4

6

8

10

12

14

0.15-0.65

0.67-1.14

1.15-2.04

2.16-2.63

2.69-3.33

3.69-5.32

5.64-8.49

8.84-20.00



36

Defaults 2 Years Later

EDF Range

Number

of Firms


0

2

4

6

8

10

12

14

0.15-0.65

0.67-1.14

1.15-2.04

2.16-2.63

2.69-3.33

3.69-5.32

5.64-8.49

8.84-20.00



37


EDF Range

Number

of Firms


0

2

4

6

8

10

12

14

0.15-0.65

0.67-1.14

1.15-2.04

2.16-2.63

2.69-3.33

3.69-5.32

5.64-8.49

8.84-20.00



38


EDF Range

Number

of Firms


0

2

4

6

8

10

12

14

0.15-0.65

0.67-1.14

1.15-2.04

2.16-2.63

2.69-3.33

3.69-5.32

5.64-8.49

8.84-20.00



39


EDF Range

Number

of Firms


0

2

4

6

8

10

12

14

0.15-0.65

0.67-1.14

1.15-2.04

2.16-2.63

2.69-3.33

3.69-5.32

5.64-8.49

8.84-20.00

• 103 Non-Financials Rated Single B as of December 1992• 14 Defaults in 4 Years• 13 defaults from the above-median EDF companies

• Non-Defaulting firms had 2.26% EDF• Defaulting firms had 13.89% EDF

Equally rated firms are not the same risk

Market data can add precision to traditional analysis and accounting-based evaluations



40

EDF Predictive Power

Random Chance



41

EDF Prior to DefaultTotal Universe

0

1

2

3

4

5

6

7

8

9

10

-5 yr

s

-4 yr

s

-3 yr

s

-2 yr

s-1

yr 0

EDF Provides Early Warning

1 to 60 Months Prior to Default

Median EDF of firms that subsequently default

Weakest Quartile EDF all firms

Benchmark: Median EDF for period for all firms



42




0

1

2

3

4

5

6

7

8

9

10

-5 yr

s

-4 yr

s

-3 yr

s

-2 yr

s-1

yr 0

Weakest Quartile EDF, firms that subsequently default

Best Quartile EDF, firms that subsequently default






43




0

1

2

3

4

5

6

7

8

9

10

-5 y

rs

-4 y

rs

-3 y

rs

-2 y

rs

-1 y

r 0

Weakest Quartile EDF, firms that subsequently default

Best Quartile EDF, firms that subsequently default






44

EDF Predictive PowerValidated Defaults in Firms with $300mm or more in sales



45

50%

55%

60%

65%

70%

75%

80%

85%

90%

-1-3-6-9-12Months before upgrade/downgrade

Non-investment gradeUpgrades

Investment gradeDowngrades

Non-investmentDowngrades

Investment grade Upgrades

Upgrade/Downgrade Study

The test was fairly conservative – to signal a ratings change, a firm had to have an EDF™ credit measure that indicated a full notch or more difference at the point X months ahead of the rating change. This means the EDF had to be 2 or more times the EDF of its grade.



46

To Learn More

Please contact your Moody’s KMV client representative or visit us online at www.moodyskmv.com.

Contact Moody’s KMV via e-mail at [email protected]

or call us at:

NORTH AND SOUTH AMERICA, CALL:

+1 (866) 321-MKMV (6568) or +1 (415) 296-9669

EUROPE, THE MIDDLE EAST, AFRICA, CALL:

+44 (20) 7778-7400

ASIA PACIFIC, CALL:

+81 (3) 3218-1160

Measuring & Managing Credit Risk: Understanding the EDF Credit Measure for Public Firms 2004.

Documents

edf credit measure edf

measuring managing credit

current edf credit measure

credit section

credit risk portfolio

credit portfolios

dynamics of credit risk

credit quality slide