Risk Modeling: Practical Applications of Artificial Intelligence, Machine Learning, and Deep Learning

ISBN-13: 9781119824930 / Angielski / Twarda / 2022

Stephen J. Tonna

Spis treści

Acknowledgments xiPreface xiiiChapter 1 Introduction 1Risk Modeling: Definition and Brief History 4Use of AI and Machine Learning in Risk Modeling 7The New Risk Management Function 7Overcoming Barriers to Technology and AI Adoption with a Little Help from Nature 10This Book: What It Is and Is Not 11Endnotes 12Chapter 2 Data Management and Preparation 15Importance of Data Governance to the Risk Function 18Fundamentals of Data Management 20Other Data Considerations for AI, Machine Learning, and Deep Learning 22Concluding Remarks 29Endnotes 30Chapter 3 Artificial Intelligence, Machine Learning, and Deep Learning Models for Risk Management 31Risk Modeling Using Machine Learning 35Definitions of AI, Machine, and Deep Learning 40Concluding Remarks 52Endnotes 52Chapter 4 Explaining Artificial Intelligence, Machine Learning, and Deep Learning Models 55Difference Between Explaining and Interpreting Models 57Why Explain AI Models 59Common Approaches to Address Explainability of Data Used for Model Development 61Common Approaches to Address Explainability of Models and Model Output 62Limitations in Popular Methods 68Concluding Remarks 69Endnotes 69Chapter 5 Bias, Fairness, and Vulnerability in Decision-Making 71Assessing Bias in AI Systems 73What Is Bias? 76What Is Fairness? 77Types of Bias in Decision-Making 78Concluding Remarks 89Endnotes 89Chapter 6 Machine Learning Model Deployment, Implementation, and Making Decisions 91Typical Model Deployment Challenges 93Deployment Scenarios 98Case Study: Enterprise Decisioning at a Global Bank 101Practical Considerations 102Model Orchestration 103Concluding Remarks 104Endnote 104Chapter 7 Extending the Governance Framework for Machine Learning Validation and Ongoing Monitoring 105Establishing the Right Internal Governance Framework 108Developing Machine Learning Models with Governance in Mind 109Monitoring AI and Machine Learning 112Compliance Considerations 122Further Takeaway 125Concluding Remarks 126Endnotes 127Chapter 8 Optimizing Parameters for Machine Learning Models and Decisions in Production 129Optimization for Machine Learning 131Machine Learning Function Optimization Using Solvers 133Tuning of Parameters 136Other Optimization Algorithms for Risk Models 141Machine Learning Models as Optimization Tools 143Concluding Remarks 147Endnotes 148Chapter 9 The Interconnection between Climate and Financial Instability 149Magnitude of Climate Instability: Understanding the "Why" of Climate Change Risk Management 152Interconnected: Climate and Financial Stability 157Assessing the impacts of climate change using AI and machine learning 158Using scenario analysis to understand potential economic impact 160Practical Examples 170Concluding Remarks 172Endnotes 172About the Authors 175Index 177

O autorze

TERISA ROBERTS, PHD, is Global Solution Lead for Risk Modeling and Decisioning at SAS. She has nearly twenty years of experience in quantitative risk management and advanced analytics. She regularly advises banks and regulators around the world on industry best practices in AI, automation, and digitalization related to risk modeling and decisioning.STEPHEN J. TONNA, PHD, is a Senior Banking Solutions Advisor at SAS. He is a member of the SAS Risk Finance Advisory team for SAS Risk Research and Quantitative Solutions (RQS) in Asia Pacific. He received his doctorate in genetics, mathematics, and statistics from the University of Melbourne and research fellowship from the Brigham and Women's Hospital and Harvard Medical School.