Risk Modeling: Practical Applications of Artificial Intelligence, Machine Learning, and Deep Learning (Wiley and SAS Business Series)

✍ Scribed by Terisa Roberts, Stephen J. Tonna

• Publisher: Wiley
• Year: 2022
• Tongue: English
• Leaves: 205
• Edition: 1
• Category: Library

✦ Synopsis

A wide-ranging overview of the use of machine learning and AI techniques in financial risk management, including practical advice for implementation 

Risk Modeling: Practical Applications of Artificial Intelligence, Machine Learning, and Deep Learning introduces readers to the use of innovative AI technologies for forecasting and evaluating financial risks. Providing up-to-date coverage of the practical application of current modelling techniques in risk management, this real-world guide also explores new opportunities and challenges associated with implementing machine learning and artificial intelligence (AI) into the risk management process.  

Authors Terisa Roberts and Stephen Tonna provide readers with a clear understanding about the strengths and weaknesses of machine learning and AI while explaining how they can be applied to both everyday risk management problems and to evaluate the financial impact of extreme events such as global pandemics and changes in climate. Throughout the text, the authors clarify misconceptions about the use of machine learning and AI techniques using clear explanations while offering step-by-step advice for implementing the technologies into an organization’s risk management model governance framework. This authoritative volume: 

• Highlights the use of machine learning and AI in identifying procedures for avoiding or minimizing financial risk 
• Discusses practical tools for assessing bias and interpretability of resultant models developed with machine learning algorithms and techniques 
• Covers the basic principles and nuances of feature engineering and common machine learning algorithms 
• Illustrates how risk modeling is incorporating machine learning and AI techniques to rapidly consume complex data and address current gaps in the end-to-end modelling lifecycle 
• Explains how proprietary software and open-source languages can be combined to deliver the best of both worlds: for risk models and risk practitioners  

Risk Modeling: Practical Applications of Artificial Intelligence, Machine Learning, and Deep Learning is an invaluable guide for CEOs, CROs, CFOs, risk managers, business managers, and other professionals working in risk management. 

✦ Table of Contents

Cover
Title Page
Copyright Page
Contents
Acknowledgments
Preface
Chapter 1 Introduction
Risk Modeling: Definition and Brief History
Use of AI and Machine Learning in Risk Modeling
The New Risk Management Function
Overcoming Barriers to Technology and AI Adoption with a Little Help from Nature
This Book: What It Is and Is Not
Endnotes
Chapter 2 Data Managementand Preparation
Importance of Data Governance to the Risk Function
Fundamentals of Data Management
Master Data Management
Standardizing Datasets and Ensuring Data Quality
Other Data Considerations for AI, Machine Learning, and Deep Learning
Utilizing “Alternative Data”
Extending Risk Data to “Alternative Data” for AI and Machine Learning
Synthetic Data Generation
Typical Data Preprocessing, Including Feature Engineering
Concluding Remarks
Endnotes
Chapter 3 Artificial Intelligence, Machine Learning, and Deep Learning Models for Risk Management
Risk Modeling Using Machine Learning
Tier 1 Commercial Bank in Latin America
Tier 1 Financial Institution in Asia Pacific
Process Automation for Claims Processing
Navigating through the Storm of COVID-19
Approximation of Complex Risk Calculations
Definitions of AI, Machine, and Deep Learning
Artificial Intelligence
Machine Learning
Deep Learning
Putting It All Together
Concluding Remarks
Endnotes
Chapter 4 Explaining Artificial Intelligence, Machine Learning, and Deep Learning Models
Difference Between Explaining and Interpreting Models
Why Explain AI Models
Common Approaches to Address Explainability of Data Used for Model Development
Common Approaches to Address Explainability of Models and Model Output
Limitations in Popular Methods
Concluding Remarks
Endnotes
Chapter 5 Bias, Fairness, and Vulnerability in Decision-Making
Assessing Bias in AI Systems
What Is Bias?
What Is Fairness?
Types of Bias in Decision-Making
Current Guidance, Laws, and Regulations
Methods and Measures to Address Bias and Fairness
Using AI and Machine Learning to Detect and Remediate Bias: A Word of Caution
Vulnerability
Concluding Remarks
Endnotes
Chapter 6 Machine Learning Model Deployment, Implementation, and Making Decisions
Typical Model Deployment Challenges
Lack of Structured Deployment Processes
The Need to Manually Recode Complex Models
Managing Multiple Analytical Tools and Programming Languages
Signoff and Approvals
Adoption of Agile Practices for ModelOps
Deployment Scenarios
Deploying Models in Batch Processes
Deploying Models in Real Time
Deployment of Models in Database Management Systems
Deployment of Models to Lightweight Containers
Deployments in Business Decision Workflows
Case Study: Enterprise Decisioning at a Global Bank
Practical Considerations
Begin with the End in Mind
Continuous Model Monitoring
Model Orchestration
Concluding Remarks
Endnote
Chapter 7 Extending the Governance Framework for Machine Learning Validation and Ongoing Monitoring
Establishing the Right Internal Governance Framework
Developing Machine Learning Models with Governance in Mind
Model Decay
Stability
Population Drift
Feature Drift
Robustness, Benchmarking, and Backtesting
Interpretability
Variable Importance
Partial Dependence
Individual Conditional Expectation
Shapley Values
Anomaly Detection
Bias
Compliance Considerations
GDPR (Global Data Protection Regulation)
ECOA (Equal Credit Opportunity Act)
SR-Letter 11-7
EU Guidelines for Trustworthy AI
Further Takeaway
Concluding Remarks
Endnotes
Chapter 8 Optimizing Parameters for Machine Learning Models and Decisions in Production
Optimization for Machine Learning
Solvers for When the Target Objective Function Is Convex
Tuning of Parameters
Other Optimization Algorithms for Risk Models
Logistic Regression
Neural Networks
Decision Science Optimization Tool to Reduce Credit Decisioning Policy Rules
Concluding Remarks
Endnotes
Chapter 9 The Interconnection between Climate and Financial Stability
Magnitude of Climate Instability: Understanding the “Why” of Climate Change Risk Management
Climate Change Crisis: Not Just about CO2 Emissions
United Nations and Climate Change
Limitations of the Paris Accord Target
Interconnected: Climate and Financial Stability
Assessing the impacts of climate change using AI and machine learning
Using scenario analysis to understand potential economic impacts
Regulatory Guidance and Compliance Measures
Stress Testing: Getting a Foot in the Door
Firms Can Start by Strengthening Their Analytics Frameworks
Practical Examples
Climate Risk Management Solution
Environmental, Social, and Governance Application in APAC-Based Financial Companies
Sustainability Investment Screening
Concluding Remarks
Endnotes
About the Authors
Index
EULA