Estimating Multiple Risk Measurements for Internal and External Audiences Using a Manageable Approach: Stress Testing Structured Portfolios YANIV GERSHON , STATE STREET JUAN CARLOS CALCAGNO, MOODY’S ANALYTICS
Outline » Discuss project aimed to stress test State Street structured portfolio o Describe standard modeling approach for diverse assets and regions o Explain economic stress testing framework and assumptions o Internal and external applications for Credit risk economic capital Reserve requirements Research, development, and investment
Overview of Project Model Macro Forecast Deal-Level Security-Level Different uses Behavioral Estimation Assumptions Cash-flows at State Street Assumptions Collateral Performance CDR ECAP Default Vector Principal and Severity interest CreditCycle – Choose your payments OTTI Process Cash-Flow Behavioral Macro Scenario Engine Model Loss Estimation Severity Vector Stress Test CPR Program Economic Prepayment Vector Parameters (GDP, HPI, employment
DATA, MODELS AND ESTIMATION
Moody's Performance Data Service (PDS) Our data and modeling team collects, normalizes and stores data Scrubbing, validation & standardization Data collection Accessible Data Data warehousing 4.7199998 4.7199998 4.9333301 4.7199998 4.7199998 4.9333301 5.4699998 5.4699998 5.3666701 5.4699998 5.4699998 5.3666701 Software Suite 5.6399999 5.6399999 6.0666699 5.6399999 5.6399999 6.0666699 6.25 6.25 6.8666701 6.25 6.25 6.8666701 00000000000000000 6.7122302 6.6847372 8.0736609 6.7122302 6.6847372 8.0736609 7.3008995 7.1676712 8.6520376 7.3008995 7.1676712 8.6520376 0000000000000000000000 8.136611 7.7857828 9.1786413 8.136611 7.7857828 9.1786413 10 10 8.6848841 7.9900608 9.4953976 8.6848841 7.9900608 9.4953976 8 00000000000000000000 9.2574759 8.0914431 9.7242556 9.2574759 8.0914431 9.7242556 6 9.1450596 7.4228692 9.7663956 9.1450596 7.4228692 9.7663956 8.7279348 6.5703249 9.6879368 4 8.7279348 6.5703249 9.6879368 0000000000000 8.2612009 5.9571881 9.386632 2 8.2612009 5.9571881 9.386632 7.8519301 5.603909 8.9864655 0 7.8519301 5.603909 8.9864655 000000000000000000000000 00000000000000000000000 0000000000000000000000 00000000000000000000 0000000000000 Direct Download 4.7199998 4.7199998 4.9333301 4.7199998 4.7199998 4.9333301 000000000000000000000000 5.4699998 5.4699998 5.3666701 5.4699998 5.4699998 5.3666701 5.6399999 5.6399999 6.0666699 5.6399999 5.6399999 6.0666699 00000000000000000000000 6.25 6.25 6.8666701 6.25 6.25 6.8666701 4.7199998 4.7199998 4.9333301 6.7122302 6.6847372 8.0736609 6.7122302 6.6847372 8.0736609 5.4699998 5.4699998 5.3666701 5.6399999 5.6399999 6.0666699 0000000000000000000000 7.3008995 7.1676712 8.6520376 7.3008995 7.1676712 8.6520376 6.25 6.25 6.8666701 6.7122302 6.6847372 8.0736609 8.136611 7.7857828 9.1786413 8.136611 7.7857828 9.1786413 7.3008995 7.1676712 8.6520376 8.6848841 7.9900608 9.4953976 8.6848841 7.9900608 9.4953976 00000000000000000000 8.136611 7.7857828 9.1786413 8.6848841 7.9900608 9.4953976 9.2574759 8.0914431 9.7242556 9.2574759 8.0914431 9.7242556 9.2574759 8.0914431 9.7242556 9.1450596 7.4228692 9.7663956 9.1450596 7.4228692 9.7663956 9.1450596 7.4228692 9.7663956 8.7279348 6.5703249 9.6879368 8.2612009 5.9571881 9.386632 8.7279348 6.5703249 9.6879368 8.7279348 6.5703249 9.6879368 7.8519301 5.603909 8.9864655 8.2612009 5.9571881 9.386632 8.2612009 5.9571881 9.386632 7.8519301 5.603909 8.9864655 7.8519301 5.603909 8.9864655 2 3 Data warehouse is constructed Data sets, performance An automated program sorts 4 1 Collect pool, deal, tranche and from scrubbed data, and is made reports and indexes would and cleans the data, then a loan level data from originators, available for use in the software be available to end users team of specialists manually servicers and rating agencies. or accessible via direct download validates and scrub key fields Over 13,000 deals back to 1980s and over 50 performance metrics 5
Data Coverage ABS/RMBS Deals Number of Unique Number of Unique Pools Pools Asset Class Product Line Asset Class Product Line Market as Feb 2011 Market as Feb 2011 USA RMBS 11,689 Auto 251 Subprime 3,530 Prime 176 Alt-A 4,562 Marginal 17 Jumbo 2,327 Subprime 58 Other 507 Prime Conforming 1 Motorcycles 49 Option Arms 762 Credit Cards 37 USA HEL 275 Bank 24 HELOC 212 Charge 2 Home Equity/Closed End 63 Retail 6 Australia 136 Student Loans 348 Greece 9 FFELP 238 Ireland 22 Private 79 Italy 92 Mixed 31 Netherlands 107 Portugal 30 TOTAL 685 Russia 12 Spain 226 UK 141 TOTAL 12,739 6
Highlights of credit risk models » A comprehensive approach based on a series of econometric models, each designed to capture a specific component of pool behaviour – pipeline, prepayment, default and severity » Model generates correlations between performance and macroeconomic data » Correlations are estimated using ALL active and inactive deals in the market » Time series includes data covering a full business cycle » Based on multiple regression analysis, deal specific vectors are generated under alternative economic scenarios » Standardized pool-level data and similar econometric framework is used for ALL ASSETS AND COUNTRIES
Econometric Model: Dynamic Panel Data Lifecycle component Lifecycle component » Takes into account the shape of the performance curve over pools’ life Business cycle exposure component Business cycle exposure component » Explicit connection between pool performance and macroeconomic drivers = f Pool performance provides the ability to stress test holdings and run “what-if” scenarios time series (e.g., CPR, CDR, LGD Vectors) Pool & Loan-level components Pool-specific quality component » Attributes (LTV, collateral type, region, etc) define quality across pools » Early delinquencies also serve as proxies for underlying pool quality » Economic conditions at origination matter for pool quality » Econometric technique accounts for other unobserved effects
Different subsets of macroeconomic variables are used for each vector and asset type RMBS/HEL AUTO/MOTO LOANS & LEASES » Unemployment Rate-UI Claims » Home Prices » CPI New and Used Cars » Existing Home Sales » Vehicles Sales & Car Registrations » Refinancing Activity » Disposable Income » Unemployment Rate » Real GDP » Real GDP » Personal Bankruptcy Rates » Disposable Income and Wages » Interest Rate – Bank Prime Rate » Fed Funds and Mortgage Composite Rates STUDENT LOANS CREDIT CARDS » Labor Market Indicators » Wages and Disposable Income » Avg. Hourly Wages and Disposable Income » Employment ,Unemployment Rate-UI Claims » Net Worth and Debt Service Ratio » Real GDP » Interest Rate – Fed Funds » Interest Rate – Bank Prime Rate
US Auto Loans, Leases, Motorcycle, RVs and Boats: Summary of model inputs Vector Group Variable 30 day 60 day 90+ day CDR Repossession Net Chargeoff CPR Principal delinquency delinquency delinquency Origination Conditions Weighted Average Coupon (WAC) X Weighted Average Maturity (WAM) X Loan Type X X X X X X X X Unemployment Rate X X X X X X Conditions at Economic Origination Prime Rate X Used Car Prices X X X X X X New Car Prices X X X GDP t, t-3 t, t-3 t, t-3 t, t-3 t, t-3 t, t-3 t, t-3 Unemployment Rate t t t t t t t Current Economic Conditions Relative Unemployment Rate t t t t t t t Relative Prime Rate t Used Car Prices t t t t t t Relative Used Car Prices t t t t t Relative New Car Prices t t Automobile Sales t Automobile Registrations t t t t t t Personal Bankruptcies t t t t t t Mortgage Loan-to-Value Ratio t t t t t t connections 30 day delinquency t t Pipeline 60 day delinquency t 90+ day delinquency t t Notes : All models include nonlinear terms for the lifecycle (age in months), and seasonality factors (month)
Example: USA Alt-A RMBS Deal (2006 vintage) Constant Default Rate (annualized %) You can ask: “What would happen to my deal’s CDR under the 5 different scenarios given by Chief Economist Mark Zandi?” Worst Case Scenario
USE OF MODELS AT STATE STREET
Overview Model Macro Forecast Deal-Level Security-Level Different uses Behavioral Estimation Assumptions Cash-flows at State Street Assumptions Collateral Performance CDR ECAP Default Vector Principal and Severity interest CreditCycle – Choose your payments OTTI Process Cash-Flow Behavioral Macro Scenario Engine Model Loss Estimation Severity Vector Stress Test CPR Program Economic Prepayment Vector Parameters (GDP, HPI, employment
Overview » Several functions within State Street are interested in analyzing Structured Assets performance o Global Treasury – responsible for investment decisions and the Other Than Temporary Impairment (OTTI) process o Finance – responsible for State Street’s stress test program and the Fed Comprehensive Capital Analysis and Review (CCAR) program o Enterprise Risk Management - in its role of business units risk management and Credit Risk Economic Capital
Recommend
More recommend
