Machine Learning for Financial Risk Management with Python: Algorithms for Modeling Risk

Cover....1

Copyright....6

Table of Contents....7

Preface....11

Conventions Used in This Book....14

Using Code Examples....15

O’Reilly Online Learning....16

How to Contact Us....16

Acknowledgements....17

Part I. Risk Management Foundations....19

Chapter 1. Fundamentals of Risk Management....21

Risk....22

Return....22

Risk Management....25

Main Financial Risks....26

Big Financial Collapse....27

Information Asymmetry in Financial Risk Management....29

Adverse Selection....29

Moral Hazard....32

Conclusion....33

References....33

Chapter 2. Introduction to Time Series Modeling....35

Time Series Components....38

Trend....39

Seasonality....43

Cyclicality....45

Residual....46

Time Series Models....52

White Noise....53

Moving Average Model....55

Autoregressive Model....60

Autoregressive Integrated Moving Average Model....66

Conclusion....72

References....73

Chapter 3. Deep Learning for Time Series Modeling....75

Recurrent Neural Networks....76

Long-Short Term Memory....83

Conclusion....89

References....90

Part II. Machine Learning for Market, Credit, Liquidity, and Operational Risks....91

Chapter 4. Machine Learning-Based Volatility Prediction....93

ARCH Model....96

GARCH Model....102

GJR-GARCH....108

EGARCH....110

Support Vector Regression: GARCH....113

Neural Networks....119

The Bayesian Approach....124

Markov Chain Monte Carlo....126

Metropolis–Hastings....128

Conclusion....133

References....134

Chapter 5. Modeling Market Risk....137

Value at Risk (VaR)....139

Variance-Covariance Method....140

The Historical Simulation Method....146

The Monte Carlo Simulation VaR....147

Denoising....151

Expected Shortfall....159

Liquidity-Augmented Expected Shortfall....161

Effective Cost....163

Conclusion....171

References....172

Chapter 6. Credit Risk Estimation....173

Estimating the Credit Risk....174

Risk Bucketing....176

Probability of Default Estimation with Logistic Regression....188

Probability of Default Estimation with the Bayesian Model....197

Probability of Default Estimation with Support Vector Machines....203

Probability of Default Estimation with Random Forest....205

Probability of Default Estimation with Neural Network....206

Probability of Default Estimation with Deep Learning....207

Conclusion....210

References....210

Chapter 7. Liquidity Modeling....211

Liquidity Measures....213

Volume-Based Liquidity Measures....213

Transaction Cost–Based Liquidity Measures....217

Price Impact–Based Liquidity Measures....221

Market Impact-Based Liquidity Measures....224

Gaussian Mixture Model....228

Gaussian Mixture Copula Model....234

Conclusion....237

References....237

Chapter 8. Modeling Operational Risk....239

Getting Familiar with Fraud Data....242

Supervised Learning Modeling for Fraud Examination....247

Cost-Based Fraud Examination....252

Saving Score....254

Cost-Sensitive Modeling....256

Bayesian Minimum Risk....258

Unsupervised Learning Modeling for Fraud Examination....261

Self-Organizing Map....262

Autoencoders....265

Conclusion....269

References....270

Part III. Modeling Other Financial Risk Sources....271

Chapter 9. A Corporate Governance Risk Measure: Stock Price Crash....273

Stock Price Crash Measures....275

Minimum Covariance Determinant....276

Application of Minimum Covariance Determinant....278

Logistic Panel Application....288

Conclusion....296

References....297

Chapter 10. Synthetic Data Generation and The Hidden Markov Model in Finance....299

Synthetic Data Generation....299

Evaluation of the Synthetic Data....301

Generating Synthetic Data....302

A Brief Introduction to the Hidden Markov Model....310

Fama-French Three-Factor Model Versus HMM....311

Conclusion....322

References....322

Afterword....323

Index....325

About the Author....333

Colophon....333

Financial risk management is quickly evolving with the help of artificial intelligence. With this practical book, developers, programmers, engineers, financial analysts, risk analysts, and quantitative and algorithmic analysts will examine Python-based machine learning and deep learning models for assessing financial risk. Building hands-on AI-based financial modeling skills, you'll learn how to replace traditional financial risk models with ML models.

Author Abdullah Karasan helps you explore the theory behind financial risk modeling before diving into practical ways of employing ML models in modeling financial risk using Python. With this book, you will:

• Review classical time series applications and compare them with deep learning models
• Explore volatility modeling to measure degrees of risk, using support vector regression, neural networks, and deep learning
• Improve market risk models (VaR and ES) using ML techniques and including liquidity dimension
• Develop a credit risk analysis using clustering and Bayesian approaches
• Capture different aspects of liquidity risk with a Gaussian mixture model and Copula model
• Use machine learning models for fraud detection
• Predict stock price crash and identify its determinants using machine learning models