A First Course in Model Validation and Model Risk Management

A First Course in Model Validation and Model Risk Management offers robust coverage for current and future financial engineers. Useful as part of a masters program, for self-study, or as a valuable reference, the textbook explains in step-by-step, practical terms how mathematical models owned by financial institutions are essential to their public activities, including sales, trading, risk management, and internal audits. Like a diverse fleet of cars maintained by a rental car location, a bank must make sure customers can "drive" any of its models for a specific financial product. The book covers both pricing and risk models. Chapters consider modeling basics, marked-to-market and marked-to-model asset classes, market risk, credit risk, portfolio risk, operational risk, capital model risk, and financial crime, along with machine learning/AI. To support course use and practical applications, the text provides examples in Python throughout, as well as an appendix containing homework problems for all chapters, further supported by an ftp site for data and sample code. Additional appendices cover global model risk management, and a refresher in statistics.

Table of Contents:
1. Introductory Material 1.1 Why Are We Writing This Book? 1.2 Computer Code 1.3 Note on Technical Terms, Jargon, Abbreviations, and Notation 1.4 What Is Not in This Book 1.5 To the Instructor 2. Model Basics 2.1 History of MRM 2.2 What Is a Model? 2.3 What Is Model Risk? 2.4 What is MVal? 2.5 Impact of MVal 2.6 Validation Use Cases 3. Standards 3.1 Independence 3.2 Effective Challenge 3.3 Benchmarking 3.4 Testing 3.5 Vendors 4. Techniques 4.1 New Model Registration 4.2 Classification and Risk Rating 4.3 Replication 4.4 Benchmarking 4.5 Documentation 4.6 Model Governance Preview 4.7 Other Validation Testing Techniques 4.8 Postvalidation Testing, Also Called “Ongoing Monitoring” 4.9 Toolkits 4.10 Job Functions and Lines of Defense 4.11 Diplomacy and Communication 4.12 Role of Consultants 4.12 Example―Validation of Black-Scholes 5. Marked-to-Market Asset Classes 5.1 Introduction 5.2 Fixed Income 5.3 Equity 5.4 FX 5.5 Commodities 6. Marked-to-Model Asset Classes 6.1 Bonds 6.2 Exotics 6.3 Structured Credit and Securitizations 6.4 Equity Exotics 6.5 Other Asset Classes 7. Market Risk I: Statistical Measures 7.1 Value-at-Risk 7.2 VaR Decomposition 7.3 Validating VaR Assumptions 7.4 Validating VaR Inputs 7.5 VaR Backtesting 7.6 Expected Shortfall 7.7 Curing Problematic Timeseries: EWMA 8. Market Risk II: Stress Testing 8.1 Introduction 8.2 Details of CCAR Scenarios 8.3 CCAR Models 8.4 Building Stress Scenarios and Applying the Stresses to the Bank’s Positions 8.5 Internal Stress Tests 9. Issuer Credit Risk 9.1 Introduction 9.2 Philosophy of Credit Ratings 9.3 PD, LGD, and EAD 9.4 Credit Ratings in Practice 9.5 Scorecard Models 10. Counterparty Credit Risk 10.1 Valuation Adjustments 10.2 Wrong Way Risk (WWR) 10.3 Potential Future Exposure (PFE) Basics 10.4 PFE Advanced Modeling Approach (AMA) 10.5 SIMM: The Standard Initial Margin Model 11. Correlation Credit Risk 11.1 Single-Name Credit Products 11.2 Simple Correlation Products 11.3 Tranched Correlation Products 11.4 Correlation Credit and the Great Financial Crisis 12. Portfolio Risk 12.1 Equity Performance 12.2 Statistical Arbitrage 12.3 Hedge Fund Basics 12.4 Proprietary Hedge Fund Equity Models 13. Operational Risk 13.1 The Basel OR Event Types 13.2 ORX Nonfinancial Risk Levels 13.3 Standard Approach to OR Capital 13.4 Advanced Approach: OR Models 13.5 Key Risk Indicators 13.6 OR Stress Testing 14. Capital Model Risk 14.1 Regulatory Capital 14.2 History of U.S. Bank Capital 14.3 Basel Ratios and Buffers 14.4 SIFI Tests 14.5 Economic Capital 15. Artificial Intelligence Risk 15.1 Validating Pricing and Risk AI Models 15.2 MRM Assisted by AI 15.3 AI Explainability 15.4 Essentials of AI MRM 15.5 AI Use By Central Banks 15.6 AI Standards 16. Miscellaneous Topics in Model Risk 16.1 Transition From IBORs to RFRs: SOFR 16.2 Regulatory Risk 16.3 Anti—Money Laundering/Sanctions Models 16.4 Fraud Detection Models 16.5 Model Validation at Insurance Firms 16.6 The Greeks (Sensitivities) 16.7 Monte Carlo Simulations 16.8 Mortgage Model Risk 16.9 Validation of Qualitative Models 17. Model Governance Prologue 17.1 Introduction 17.2 Model Inventory 17.3 Model Restrictions 17.4 Internal Audit 17.5 Policies and Procedures 17.6 Role of Regulators 17.7 Personnel 17.8 Model Governance in Practice Appendix A: Homework Problems Appendix B: Global MRM Regulation Appendix C: Statistics Refresher Appendix D: Online Content Index

About the Author :
Jonathan Schachter holds a PhD from University of California, Berkeley, and has over 23 years of experience as a model risk professional, with a practical background in market risk, portfolio risk, operational risk, capital model risk, and AI risk. Currently Jonathan is CEO and Founder of Delta Vega Inc, and has previously held positions at Jefferies Financial and Citibank, among other firms. Martin Goldberg holds a PhD from City University of New York, and is Vice President in Model Validation at Mizuho Americas. He has held past positions at Citigroup, Bloomberg, AIG, and Chase Manhattan Bank. He is also on the Board of Directors for Rutgers University (Newark), for their Master of Quantitative Finance (MQF) Program, and has presented widely at conferences and universities on topics related to model risk assessment. Chandrakant Maheshwari is a seasoned expert in model validation with over 20 years of experience in financial risk analytics. An alum of the Indian Institute of Technology, Delhi, he is also an avid blogger and regularly publishes articles on model validation, sharing his extensive knowledge and insights in the field, and works in the financial sector.