Machine Learning for Financial Risk Management with Python

Machine Learning for Financial Risk Management with Python

by Abdullah Karasan
Released December 2021
Publisher(s): O'Reilly Media, Inc.
ISBN: 9781492085256

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Buy on Amazon Buy on ebooks.com
Start your free trial

Book 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 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

Publisher resources

View/Submit Errata

Table of contents

  1. Preface
    1. Conventions Used in This Book
    2. Using Code Examples
    3. O’Reilly Online Learning
    4. How to Contact Us
    5. Acknowledgements
  2. I. Risk Management Foundations
  3. 1. Fundamentals of Risk Management
    1. Risk
    2. Return
    3. Risk Management
      1. Main Financial Risks
      2. Big Financial Collapse
    4. Information Asymmetry in Financial Risk Management
      1. Adverse Selection
      2. Moral Hazard
    5. Conclusion
    6. References
  4. 2. Introduction to Time Series Modeling
    1. Time Series Components
      1. Trend
      2. Seasonality
      3. Cyclicality
      4. Residual
    2. Time Series Models
    3. White Noise
      1. Moving Average Model
      2. Autoregressive Model
      3. Autoregressive Integrated Moving Average Model
    4. Conclusion
    5. References
  5. 3. Deep Learning for Time Series Modeling
    1. Recurrent Neural Networks
    2. Long-Short Term Memory
    3. Conclusion
    4. References
  6. II. Machine Learning for Market, Credit, Liquidity, and Operational Risks
  7. 4. Machine Learning-Based Volatility Prediction
    1. ARCH Model
    2. GARCH Model
    3. GJR-GARCH
    4. EGARCH
    5. Support Vector Regression: GARCH
    6. Neural Networks
    7. The Bayesian Approach
      1. Markov Chain Monte Carlo
      2. Metropolis–Hastings
    8. Conclusion
    9. References
  8. 5. Modeling Market Risk
    1. Value at Risk (VaR)
      1. Variance-Covariance Method
      2. The Historical Simulation Method
      3. The Monte Carlo Simulation VaR
    2. Denoising
    3. Expected Shortfall
    4. Liquidity-Augmented Expected Shortfall
    5. Effective Cost
    6. Conclusion
    7. References
  9. 6. Credit Risk Estimation
    1. Estimating the Credit Risk
    2. Risk Bucketing
    3. Probability of Default Estimation with Logistic Regression
      1. Probability of Default Estimation with the Bayesian Model
      2. Probability of Default Estimation with Support Vector Machines
      3. Probability of Default Estimation with Random Forest
      4. Probability of Default Estimation with Neural Network
      5. Probability of Default Estimation with Deep Learning
    4. Conclusion
    5. References
  10. 7. Liquidity Modeling
    1. Liquidity Measures
      1. Volume-Based Liquidity Measures
      2. Transaction Cost–Based Liquidity Measures
      3. Price Impact–Based Liquidity Measures
      4. Market Impact-Based Liquidity Measures
    2. Gaussian Mixture Model
    3. Gaussian Mixture Copula Model
    4. Conclusion
    5. References
  11. 8. Modeling Operational Risk
    1. Getting Familiar with Fraud Data
    2. Supervised Learning Modeling for Fraud Examination
      1. Cost-Based Fraud Examination
      2. Saving Score
      3. Cost-Sensitive Modeling
      4. Bayesian Minimum Risk
    3. Unsupervised Learning Modeling for Fraud Examination
      1. Self-Organizing Map
      2. Autoencoders
    4. Conclusion
    5. References
  12. III. Modeling Other Financial Risk Sources
  13. 9. A Corporate Governance Risk Measure: Stock Price Crash
    1. Stock Price Crash Measures
    2. Minimum Covariance Determinant
    3. Application of Minimum Covariance Determinant
    4. Logistic Panel Application
    5. Conclusion
    6. References
  14. 10. Synthetic Data Generation and The Hidden Markov Model in Finance
    1. Synthetic Data Generation
    2. Evaluation of the Synthetic Data
    3. Generating Synthetic Data
    4. A Brief Introduction to the Hidden Markov Model
    5. Fama-French Three-Factor Model Versus HMM
    6. Conclusion
    7. References
  15. Afterword
  16. Index
  17. About the Author

Product information

  • Title: Machine Learning for Financial Risk Management with Python
  • Author(s): Abdullah Karasan
  • Release date: December 2021
  • Publisher(s): O'Reilly Media, Inc.
  • ISBN: 9781492085256