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

Description

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 modelsExplore volatility modeling to measure degrees of risk, using support vector regression, neural networks, and deep learningImprove market risk models (VaR and ES) using ML techniques and including liquidity dimensionDevelop a credit risk analysis using clustering and Bayesian approachesCapture different aspects of liquidity risk with a Gaussian mixture model and Copula modelUse machine learning models for fraud detectionPredict stock price crash and identify its determinants using machine learning models Cover Copyright Table of Contents Preface Conventions Used in This Book Using Code Examples O’Reilly Online Learning How to Contact Us Acknowledgements Part I. Risk Management Foundations Chapter 1. Fundamentals of Risk Management Risk Return Risk Management Main Financial Risks Big Financial Collapse Information Asymmetry in Financial Risk Management Adverse Selection Moral Hazard Conclusion References Chapter 2. Introduction to Time Series Modeling Time Series Components Trend Seasonality Cyclicality Residual Time Series Models White Noise Moving Average Model Autoregressive Model Autoregressive Integrated Moving Average Model Conclusion References Chapter 3. Deep Learning for Time Series Modeling Recurrent Neural Networks Long-Short Term Memory Conclusion References Part II. Machine Learning for Market, Credit, Liquidity, and Operational Risks Chapter 4. Machine Learning-Based Volatility Prediction ARCH Model GARCH Model GJR-GARCH EGARCH Support Vector Regression: GARCH Neural Networks The Bayesian Approach Markov Chain Monte Carlo Metropolis–Hastings Conclusion References Chapter 5. Modeling Market Risk Value at Risk (VaR) Variance-Covariance Method The Historical Simulation Method The Monte Carlo Simulation VaR Denoising Expected Shortfall Liquidity-Augmented Expected Shortfall Effective Cost Conclusion References Chapter 6. Credit Risk Estimation Estimating the Credit Risk Risk Bucketing Probability of Default Estimation with Logistic Regression Probability of Default Estimation with the Bayesian Model Probability of Default Estimation with Support Vector Machines Probability of Default Estimation with Random Forest Probability of Default Estimation with Neural Network Probability of Default Estimation with Deep Learning Conclusion References Chapter 7. Liquidity Modeling Liquidity Measures Volume-Based Liquidity Measures Transaction Cost–Based Liquidity Measures Price Impact–Based Liquidity Measures Market Impact-Based Liquidity Measures Gaussian Mixture Model Gaussian Mixture Copula Model Conclusion References Chapter 8. Modeling Operational Risk Getting Familiar with Fraud Data Supervised Learning Modeling for Fraud Examination Cost-Based Fraud Examination Saving Score Cost-Sensitive Modeling Bayesian Minimum Risk Unsupervised Learning Modeling for Fraud Examination Self-Organizing Map Autoencoders Conclusion References Part III. Modeling Other Financial Risk Sources Chapter 9. A Corporate Governance Risk Measure: Stock Price Crash Stock Price Crash Measures Minimum Covariance Determinant Application of Minimum Covariance Determinant Logistic Panel Application Conclusion References Chapter 10. Synthetic Data Generation and The Hidden Markov Model in Finance Synthetic Data Generation Evaluation of the Synthetic Data Generating Synthetic Data A Brief Introduction to the Hidden Markov Model Fama-French Three-Factor Model Versus HMM Conclusion References Afterword Index About the Author Colophon