AIM 1: Explain the four main reasons banks have developed credit portfolio tools.

The development and improvement of credit risk pricing models has helped in all of the following EXCEPT:

A) helping banks determine capital requirements.

B) allowing banks to use portfolio theory in the formation of new loans.

C) pricing of derivatives on risky assets.

D) None of the above (i.e., they are all the result of improved credit risk pricing models).

The correct answer is D

The banks can use CRPMs to analyze the adequacy of their reserves. The CRPM can determine the capital requirements of individual loans, which allows the use of portfolio theory in the formation of new loans. CRPMs can help price derivatives on risky assets or pools of risky assets (e.g., collateralized credit obligations). The pricing information can also be used by ratings agencies.

AIM 2: Discuss how the three risk drivers are modeled in the CreditMetrics model and list the four steps included in CreditMetrics.

1、Which of the following is not a step used in the CreditMetrics credit risk portfolio modeling process?

A) Generating correlated migration events.

B) Calibrating the multivariate non-normal distribution. 

C) Measuring “marked-to-model” losses.

D) Calculating the portfolio loss distribution.

The correct answer is B

CreditMetrics is based on a multivariate normal distribution. The four main steps used by CreditMetrics is to: gather input data, generate correlated migration events, measure “marked-to-model” losses and calculate the portfolio loss distribution.

2、With respect to computing the probability of default, CreditMetrics:

A) is a ratings-based model.

B) uses the Poisson distribution.

C) is useless.

D) None of the above.

The correct answer is A

CreditMetrics is a ratings-based model. It uses probabilities from transition matrices that show the probability of an asset having its rating changed.

3、With respect to computing loss given default, CreditMetrics:

A) uses simulations from the beta distribution.

B) uses a linear factor model.

C) is useless.

D) None of the above.

The correct answer is A

For loss given default, the CreditMetrics uses simulations from the beta distribution. Each industry has a beta distribution calibrated to describe the recovery rates for defaults in that industry. Using the specific beta distribution associated with the position’s industry, CreditMetrics draws random recovery rates and assigns the values to the defaulted positions.

4、The first step of CreditMetrics would include all of the following EXCEPT:

A) calibrating the Poisson distribution.

B) calculating the probability of default.

C) gathering yield curve data.

D) None of the above (i.e., they are all part of the first step of CreditMetrics).

The correct answer is A

The Poisson distribution is not part of CreditMetrics. The first step consists of the gathering of inputs. The gathering includes calculating many measures such as probability of default, recovery rate statistics, factor correlations and their relationships to the obligors, yield curve data, and individual exposures that are distinct from the other inputs.

AIM 3: Describe Portfolio Manager and its similarity to CreditMetrics.

1、Portfolio Manager and CreditMetrics:

A) use the same number of factors.

B) are different in that Portfolio Manager uses fewer factors than CreditMetrics.

C) are different in that Portfolio Manager uses more factors than CreditMetrics.

D) do not use a factor approach.

The correct answer is B

Portfolio Manager has only one factor, while CreditMetrics has several factors.

2、Which of the following statements, with respect to KMV’s Portfolio Manager and its similarity to CreditMetrics, is the most correct?

A) They are both based on multivariate distributions.

B) They are both based on one factor.

C) They both only focus on defaults.

D) They are very different, and have very little in common.

The correct answer is A

KMV's Portfolio Manager and CreditMetrics are very similar. They are both based on multivariate distribution. However, Portfolio Manager is unique in that it only has one factor, and it focuses on default losses.

AIM 4: List the improvements and novelties that apply to the Portfolio Risk Tracker.

rtfolio Risk Tracker is:

A) not dynamic at all.

B) dynamic but less dynamic than CreditMetrics.

C) more dynamic than CreditMetrics.

D) equally dynamic as CreditMetrics.

The correct answer is C

Portfolio Risk Tracker allows for a dynamic analysis over multiple horizons, and this is the nature of the improvements and novelties it has over CreditMetrics and other “static” risk models. For a given horizon of, say, four years, Portfolio Risk Tracker will simulate risk factors for the end of each of the four years.

AIM 5: Explain how CreditPortfolioView models default risk.

1、CreditPortfolioView models the transition matrices using:

A) agency ratings in an econometric model.

B) macroeconomic or economic cycle data in an econometric model.

C) agency ratings in a Poisson model.

D) macroeconomic or economic cycle data in a beta distribution model.

The correct answer is B

CreditPortfolioView models the transition matrices using macroeconomic or economic cycle data, and this is its primary distinguishing feature. Macroeconomic variables are the key drivers of default rates, and the CreditPortfolioView estimates an econometric model for an index that drives the default rates of an industrial sector.

2、CreditPortfolioView uses its model to simulate:

A) default rates, which are then transformed into index values.

B) neither index values nor default rates.

C) default rates only, and indices do not play a role in the process.

D) index values, which are then transformed into default rates.

The correct answer is D

The procedure can be summarized in four steps: 1) measuring the autoregressive process of the macroeconomic variables, 2) composing sector indices with the variables, 3) estimating a default rate based upon the value of that index, and 4) comparing the simulated values to historical values to determine the transition matrix to use.

AIM 6: Explain CreditRisk+ and its weaknesses.

1、With respect to CreditRisk+, which of the following is FALSE?

A) CreditRisk+ works well with data that have fat-tails.

B) CreditRisk+ only focuses on default events and ignores prices, spreads and credit migrations.

C) Factor correlations are not addressed with the CreditRisk+ model.

D) CreditRisk+ may not be appropriate for use with portfolios that do not use a buy-and-hold strategy.

The correct answer is A

CreditRisk+ only focuses on default events and ignores prices, spreads and credit migrations. In addition, factor correlations are not addressed with the CreditRisk+ model and it may not be appropriate for use with portfolios that do not use a buy-and-hold strategy. Because the model does not consider factor correlations it may not capture events associated with fat-tailed distributions.

2、A weakness of CreditRisk+ is that it:

A) does not address factor correlations.

B) ignores actuarial data.

C) cannot be used for buy-and-hold strategies.

D) does not use the Poisson distribution.

The correct answer is A

The factor correlations are not addressed in the approach. Not including correlations could reduce the ability to capture outcomes associated with fat-tailed distributions. The other three possible answers are incorrect in that CreditRisk+ uses an actuarial approach and the Poisson distribution, and it most readily applies to buy-and-hold strategies.

AIM 7: Define expected loss, unexpected loss, value at risk, economic capital, and expected shortfall.

1、An unexpected loss is defined as:

A) the standard deviation of portfolio losses. 

B) the product of the exposure, the probability of default, and the loss given default.

C) the amount of capital needed as a buffer to avoid insolvency.

D) the average or expected value of all losses greater than the VAR. 

The correct answer is A

Unexpected loss is defined as the standard deviation of portfolio losses. Expected loss is the product of the exposure, the probability of default, and the loss given default. Economic capital is the amount of capital needed as a buffer to avoid insolvency, and expected shortfall is the average or expected value of all losses greater than the VAR

2、The measure known as “unexpected loss” is best described as:

A) the average of losses greater than VAR.

B) None of the above.

C) the average of losses less than VAR.

D) the confidence level of VAR.

The correct answer is B

Unexpected loss is the standard deviation of portfolio losses. It does not directly relate to VAR.

3、Subtracting the expected loss from VAR gives the measure known as:

A) unexpected loss.

B) economic capital.

C) expected shortfall.

D) hazard rate.

The correct answer is B

Economic capital = VAR – E(LP). It is an amount of capital needed as a buffer to avoid insolvency.

4、Assume a portfolio consists of two loans of $1,000 with a correlation between loans of 0. Also, assume the only two outcomes for each loan with equal probability are a loan loss of $8 or $12. Note that the average loss for each position is $10 and the expected loss on the portfolio is $20. Find ULp, the unexpected loss of the portfolio.

A) $2.83.

B) $0.71.

C) $8.00.

D) $10.00.

The correct answer is A

E(Li) = $10, E(Lp) = $20,

ULp = ((0.25)(16 ? 20)2 + (0.5)(20 ? 20)2 + (0.25)(24 ? 20)2)0.5 = $2.828.

5、The expected loss given that the loss has exceeded the VAR is best described as the

A) expected shortfall.

B) unexpected loss.

C) economic capital.

D) Poisson parameter.

The correct answer is A

Expected shortfall is essentially an average or expected value of all losses greater than the VAR. An expression for this is: E[LP | LP > VAR].

AIM 8: Explain, including equations, the individual contribution to unexpected losses.

Assume a portfolio consists of two loans of $1,000 with a correlation between loans of 0. Also, assume the unexpected loss of both loans is $2 and portfolio unexpected loss is $2.828. Find RC1, the risk contribution of loan 1 to unexpected losses.

A) $0.71.

B) $1.41.

C) $2.

D) $2.83.

The correct answer is B

The sum of each individual risk contribution will equal the unexpected loss of the portfolio.

The risk contribution to loan 1 = UL1 ×(UL1 + ρ×UL2) / ULP

RC1 = 2 × (2 + 0(2))/2.828 = 1.4144.