Forecasting Consistent Credit & Market Risk Losses
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses
JOSE CANALS-CERDA, Federal Reserve Bank of Philadelphia JUAN M. LICARI, Senior Director, Moody’s Analytics
OCTOBER 2015
Agenda
1. Data and model pitfalls when forecasting portfolio credit losses for stress test analysis 2. Transmission mechanisms: from scenario simulations to conditional risk parameter realizations 3. Producing consistent credit and market risk projections
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
2
Transmission Mechanisms: from scenario simulations to conditional risk parameter realizations
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
Forward-Looking Scenario Generation & Severity Ranking 4
GDP Growth, % Q/Q: Forecasts per Quarter
+Q1
+Q2
+Q3
+Q4
+Q5
+Q6
+Q7
+Q8
Max Cumulative Drop in GDP growth Scatter over Marginal Rank Order
.15 .1
Max cumulative drop in GDP Growth
0
.05
Density
.2
.25
Density Function
+Q9
Cumulative Proportion
-6
-4
-2
0
2
Example of a Marginal Loading into Overall Scenario Rank-Ordering Algorithm
-5
0
5 10 15 Max Drop in Cumulative GDP Growth, %
20
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
4
Severity of Alternative Macroeconomic Scenarios Core Macro Series Across Scenario Blocks (Rank-Ordering Outcome)
Unemployment Rate, %: Over Scenario Blocks
12 10 8
-6
4
-4
6
-2
0
2
Unemployment Rate, %
14
16
4
GDP Growth, % Q/Q: Over Scenario Blocks
Block 1
Block 2
Block 3
Block 4
Block 5
Block 1
Block 2
Block 3
Block 4
Block 5
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
5
Severity of Alternative Macroeconomic Scenarios Scenario Probabilities
GDP Growth, Q/Q % -- Alternative Severity Points 1 Severity_0_50 Severity_0_99
Severity_0_90 Severity_0_999
Severity_0_95 Severity_0_9999
0.5
0 1 -0.5
-1
2
3
4
5
6
7
8
9
Prob of better outcome 0.0041708 0.0455886
CCAR Baseline ECCA's s1
0.0625286
ECCA's Baseline
0.145155 0.206814 0.8314903 0.8857924 0.9210755
ECCA's s2 ECCA's s5 CCAR Adverse ECCA's s3 ECCA's s6 CCAR Severely Adverse ECCA's s4
0.9801373 0.9907705
Scenario
-1.5
-2
-2.5
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
6
Conditional Risk Parameter Realizations Impact on Government Bond Yields
Government Bond Yields - Leading Maturities Simulations over Scenario Blocks (1 for Good , 5 for Stressed) at +Q9 1 Year 20 15
5 Years
10 Years 15 10 5 0
Yields, %
20 15 10 5
10 0
Block 1 Block 2 Block 3 Block 4 Block 5
20
Block 1 Block 2 Block 3 Block 4 Block 5
0
Yields, %
5
Yields, %
10 5 0
Yields, %
15
3 Months
Block 1 Block 2 Block 3 Block 4 Block 5
Block 1 Block 2 Block 3 Block 4 Block 5
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
7
Conditional Risk Parameter Realizations (cont.) Impact on Government Bond Yields (cont.)
Government Bond Yield Curves
10 5 0
Yields, %
15
20
Box-Plots Across Maturities at +Q9
3m
6m
1y
2y
3y
5y
7y
10y
20y
30y
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
8
Conditional Risk Parameter Realizations (cont.) Impact on Government Bond Yields (cont.)
Yield Curve Slope (10y vs. 3m Spread, %) Analysis Over Quarters and Simulations Box-Plot for +Q9
.4 .2 0
Density
.6
Distribution for +Q9
0
2 4 6 8 10 Term Premium (10y vs. 3m Spread, %)
0
2
4
6
8
10
Box-Plots, all +Qs
0
Yield Curve Slope
10 8 6 4 2 0
Yield Curve Slope
+Q9 Values over Simulations
2 4 6 8 10 Yield Curve Slope (10y vs. 3m Spread, %)
0 5000 10000 15000 20000 25000 Simulation id (1 for Good , 25000 for Stressed)
+Q1 +Q2 +Q3 +Q4 +Q9 +Q6 +Q7 +Q8 +Q9
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
9
Conditional Risk Parameter Realizations (cont.) Impact on Credit Spreads for Financials - over maturities and rating classes
Corporate Spread Curves - Financials 5 Quarters out of Sample (+Q5) - Across Rating Classes A
10 0
5
Spread, %
1.5 1 .5 0
Spread, %
2
15
Aaa
3m
1y
3y
5y
7y
10y 20y 30y
3m
1y
3y
5y
7y
10y 20y 30y
0
5
10 15 20 25
Spread, %
15 10 5 0
Spread, %
10y 20y 30y
B
20
Bbb
7y
3m
1y
3y
5y
7y
10y 20y 30y
3m
1y
3y
5y
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
10
Conditional Risk Parameter Realizations (cont.) Impact on 5Y Credit Spreads for Financials - over quarters and rating classes
Corporate Spreads over Quarters-out-of-sample Financials - 5 Year Maturity - Across Rating Classes A 15
B
0
5
Spread, %
15 10 5
10 0
Bbb 10 15 20 25
+Q1 +Q2 +Q3 +Q4 +Q5 +Q6 +Q7 +Q8 +Q9
20
+Q1 +Q2 +Q3 +Q4 +Q5 +Q6 +Q7 +Q8 +Q9
0
Spread, %
5
Spread, %
1 .5 0
Spread, %
1.5
Aaa
+Q1 +Q2 +Q3 +Q4 +Q5 +Q6 +Q7 +Q8 +Q9
+Q1 +Q2 +Q3 +Q4 +Q5 +Q6 +Q7 +Q8 +Q9
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
11
Concluding Remarks
» Generating dynamic scenario simulations » Challenges in quantifying scenario probabilities » Leveraging stress testing models to produce consistent forward-looking market risk projections » Flexible framework to consolidate credit and market risk analysis (through stress testing equations)
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
12
moodys.com
Juan M. Licari, Ph.D. Senior Director +44 (0)20.7772.1208 tel +44 (0)7800.991318 mobile [email protected] Moody's Analytics UK Ltd.
© 2015 Moody’s Analytics, Inc. and/or its licensors and affiliates (collectively, “MOODY’S”). All rights reserved. ALL INFORMATION CONTAINED HEREIN IS PROTECTED BY COPYRIGHT LAW AND NONE OF SUCH INFORMATION MAY BE COPIED OR OTHERWISE REPRODUCED, REPACKAGED, FURTHER TRANSMITTED, TRANSFERRED, DISSEMINATED, REDISTRIBUTED OR RESOLD, OR STORED FOR SUBSEQUENT USE FOR ANY SUCH PURPOSE, IN WHOLE OR IN PART, IN ANY FORM OR MANNER OR BY ANY MEANS WHATSOEVER, BY ANY PERSON WITHOUT MOODY’S PRIOR WRITTEN CONSENT. All information contained herein is obtained by MOODY’S from sources believed by it to be accurate and reliable. Because of the possibility of human or mechanical error as well as other factors, however, all information contained herein is provided “AS IS” without warranty of any kind. Under no circumstances shall MOODY’S have any liability to any person or entity for (a) any loss or damage in whole or in part caused by, resulting from, or relating to, any error (negligent or otherwise) or other circumstance or contingency within or outside the control of MOODY’S or any of its directors, officers, employees or agents in connection with the procurement, collection, compilation, analysis, interpretation, communication, publication or delivery of any such information, or (b) any direct, indirect, special, consequential, compensatory or incidental damages whatsoever (including without limitation, lost profits), even if MOODY’S is advised in advance of the possibility of such damages, resulting from the use of or inability to use, any such information. The ratings, financial reporting analysis, projections, and other observations, if any, constituting part of the information contained herein are, and must be construed solely as, statements of opinion and not statements of fact or recommendations to purchase, sell or hold any securities. NO WARRANTY, EXPRESS OR IMPLIED, AS TO THE ACCURACY, TIMELINESS, COMPLETENESS, MERCHANTABILITY OR FITNESS FOR ANY PARTICULAR PURPOSE OF ANY SUCH RATING OR OTHER OPINION OR INFORMATION IS GIVEN OR MADE BY MOODY’S IN ANY FORM OR MANNER WHATSOEVER. Each rating or other opinion must be weighed solely as one factor in any investment decision made by or on behalf of any user of the information contained herein, and each such user must accordingly make its own study and evaluation of each security and of each issuer and guarantor of, and each provider of credit support for, each security that it may consider purchasing, holding, or selling.
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
14
JOSE CANALS-CERDA, Federal Reserve Bank of Philadelphia JUAN M. LICARI, Senior Director, Moody’s Analytics
OCTOBER 2015
Agenda
1. Data and model pitfalls when forecasting portfolio credit losses for stress test analysis 2. Transmission mechanisms: from scenario simulations to conditional risk parameter realizations 3. Producing consistent credit and market risk projections
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
2
Transmission Mechanisms: from scenario simulations to conditional risk parameter realizations
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
Forward-Looking Scenario Generation & Severity Ranking 4
GDP Growth, % Q/Q: Forecasts per Quarter
+Q1
+Q2
+Q3
+Q4
+Q5
+Q6
+Q7
+Q8
Max Cumulative Drop in GDP growth Scatter over Marginal Rank Order
.15 .1
Max cumulative drop in GDP Growth
0
.05
Density
.2
.25
Density Function
+Q9
Cumulative Proportion
-6
-4
-2
0
2
Example of a Marginal Loading into Overall Scenario Rank-Ordering Algorithm
-5
0
5 10 15 Max Drop in Cumulative GDP Growth, %
20
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
4
Severity of Alternative Macroeconomic Scenarios Core Macro Series Across Scenario Blocks (Rank-Ordering Outcome)
Unemployment Rate, %: Over Scenario Blocks
12 10 8
-6
4
-4
6
-2
0
2
Unemployment Rate, %
14
16
4
GDP Growth, % Q/Q: Over Scenario Blocks
Block 1
Block 2
Block 3
Block 4
Block 5
Block 1
Block 2
Block 3
Block 4
Block 5
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
5
Severity of Alternative Macroeconomic Scenarios Scenario Probabilities
GDP Growth, Q/Q % -- Alternative Severity Points 1 Severity_0_50 Severity_0_99
Severity_0_90 Severity_0_999
Severity_0_95 Severity_0_9999
0.5
0 1 -0.5
-1
2
3
4
5
6
7
8
9
Prob of better outcome 0.0041708 0.0455886
CCAR Baseline ECCA's s1
0.0625286
ECCA's Baseline
0.145155 0.206814 0.8314903 0.8857924 0.9210755
ECCA's s2 ECCA's s5 CCAR Adverse ECCA's s3 ECCA's s6 CCAR Severely Adverse ECCA's s4
0.9801373 0.9907705
Scenario
-1.5
-2
-2.5
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
6
Conditional Risk Parameter Realizations Impact on Government Bond Yields
Government Bond Yields - Leading Maturities Simulations over Scenario Blocks (1 for Good , 5 for Stressed) at +Q9 1 Year 20 15
5 Years
10 Years 15 10 5 0
Yields, %
20 15 10 5
10 0
Block 1 Block 2 Block 3 Block 4 Block 5
20
Block 1 Block 2 Block 3 Block 4 Block 5
0
Yields, %
5
Yields, %
10 5 0
Yields, %
15
3 Months
Block 1 Block 2 Block 3 Block 4 Block 5
Block 1 Block 2 Block 3 Block 4 Block 5
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
7
Conditional Risk Parameter Realizations (cont.) Impact on Government Bond Yields (cont.)
Government Bond Yield Curves
10 5 0
Yields, %
15
20
Box-Plots Across Maturities at +Q9
3m
6m
1y
2y
3y
5y
7y
10y
20y
30y
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
8
Conditional Risk Parameter Realizations (cont.) Impact on Government Bond Yields (cont.)
Yield Curve Slope (10y vs. 3m Spread, %) Analysis Over Quarters and Simulations Box-Plot for +Q9
.4 .2 0
Density
.6
Distribution for +Q9
0
2 4 6 8 10 Term Premium (10y vs. 3m Spread, %)
0
2
4
6
8
10
Box-Plots, all +Qs
0
Yield Curve Slope
10 8 6 4 2 0
Yield Curve Slope
+Q9 Values over Simulations
2 4 6 8 10 Yield Curve Slope (10y vs. 3m Spread, %)
0 5000 10000 15000 20000 25000 Simulation id (1 for Good , 25000 for Stressed)
+Q1 +Q2 +Q3 +Q4 +Q9 +Q6 +Q7 +Q8 +Q9
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
9
Conditional Risk Parameter Realizations (cont.) Impact on Credit Spreads for Financials - over maturities and rating classes
Corporate Spread Curves - Financials 5 Quarters out of Sample (+Q5) - Across Rating Classes A
10 0
5
Spread, %
1.5 1 .5 0
Spread, %
2
15
Aaa
3m
1y
3y
5y
7y
10y 20y 30y
3m
1y
3y
5y
7y
10y 20y 30y
0
5
10 15 20 25
Spread, %
15 10 5 0
Spread, %
10y 20y 30y
B
20
Bbb
7y
3m
1y
3y
5y
7y
10y 20y 30y
3m
1y
3y
5y
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
10
Conditional Risk Parameter Realizations (cont.) Impact on 5Y Credit Spreads for Financials - over quarters and rating classes
Corporate Spreads over Quarters-out-of-sample Financials - 5 Year Maturity - Across Rating Classes A 15
B
0
5
Spread, %
15 10 5
10 0
Bbb 10 15 20 25
+Q1 +Q2 +Q3 +Q4 +Q5 +Q6 +Q7 +Q8 +Q9
20
+Q1 +Q2 +Q3 +Q4 +Q5 +Q6 +Q7 +Q8 +Q9
0
Spread, %
5
Spread, %
1 .5 0
Spread, %
1.5
Aaa
+Q1 +Q2 +Q3 +Q4 +Q5 +Q6 +Q7 +Q8 +Q9
+Q1 +Q2 +Q3 +Q4 +Q5 +Q6 +Q7 +Q8 +Q9
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
11
Concluding Remarks
» Generating dynamic scenario simulations » Challenges in quantifying scenario probabilities » Leveraging stress testing models to produce consistent forward-looking market risk projections » Flexible framework to consolidate credit and market risk analysis (through stress testing equations)
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
12
moodys.com
Juan M. Licari, Ph.D. Senior Director +44 (0)20.7772.1208 tel +44 (0)7800.991318 mobile [email protected] Moody's Analytics UK Ltd.
© 2015 Moody’s Analytics, Inc. and/or its licensors and affiliates (collectively, “MOODY’S”). All rights reserved. ALL INFORMATION CONTAINED HEREIN IS PROTECTED BY COPYRIGHT LAW AND NONE OF SUCH INFORMATION MAY BE COPIED OR OTHERWISE REPRODUCED, REPACKAGED, FURTHER TRANSMITTED, TRANSFERRED, DISSEMINATED, REDISTRIBUTED OR RESOLD, OR STORED FOR SUBSEQUENT USE FOR ANY SUCH PURPOSE, IN WHOLE OR IN PART, IN ANY FORM OR MANNER OR BY ANY MEANS WHATSOEVER, BY ANY PERSON WITHOUT MOODY’S PRIOR WRITTEN CONSENT. All information contained herein is obtained by MOODY’S from sources believed by it to be accurate and reliable. Because of the possibility of human or mechanical error as well as other factors, however, all information contained herein is provided “AS IS” without warranty of any kind. Under no circumstances shall MOODY’S have any liability to any person or entity for (a) any loss or damage in whole or in part caused by, resulting from, or relating to, any error (negligent or otherwise) or other circumstance or contingency within or outside the control of MOODY’S or any of its directors, officers, employees or agents in connection with the procurement, collection, compilation, analysis, interpretation, communication, publication or delivery of any such information, or (b) any direct, indirect, special, consequential, compensatory or incidental damages whatsoever (including without limitation, lost profits), even if MOODY’S is advised in advance of the possibility of such damages, resulting from the use of or inability to use, any such information. The ratings, financial reporting analysis, projections, and other observations, if any, constituting part of the information contained herein are, and must be construed solely as, statements of opinion and not statements of fact or recommendations to purchase, sell or hold any securities. NO WARRANTY, EXPRESS OR IMPLIED, AS TO THE ACCURACY, TIMELINESS, COMPLETENESS, MERCHANTABILITY OR FITNESS FOR ANY PARTICULAR PURPOSE OF ANY SUCH RATING OR OTHER OPINION OR INFORMATION IS GIVEN OR MADE BY MOODY’S IN ANY FORM OR MANNER WHATSOEVER. Each rating or other opinion must be weighed solely as one factor in any investment decision made by or on behalf of any user of the information contained herein, and each such user must accordingly make its own study and evaluation of each security and of each issuer and guarantor of, and each provider of credit support for, each security that it may consider purchasing, holding, or selling.
Stress Testing Challenges: Forecasting Consistent Credit & Market Risk Losses, October 2015
14
