Neural Networks in Finance

Book description

This book explores the intuitive appeal of neural networks and the genetic algorithm in finance. It demonstrates how neural networks used in combination with evolutionary computation outperform classical econometric methods for accuracy in forecasting, classification and dimensionality reduction.

Table of contents

  1. Cover image
  2. Title page
  3. Table of Contents
  4. Copyright
  5. Preface
  6. Chapter 1: Introduction
    1. 1.1 Forecasting, Classification, and Dimensionality Reduction
    2. 1.2 Synergies
    3. 1.3 The Interface Problems
    4. 1.4 Plan of the Book
  7. I: Econometric Foundations
    1. Chapter 2: What Are Neural Networks?
      1. 2.1 Linear Regression Model
      2. 2.2 GARCH Nonlinear Models
      3. 2.3 Model Typology
      4. 2.4 What Is A Neural Network?
      5. 2.5 Neural Network Smooth-Transition Regime Switching Models
      6. 2.6 Nonlinear Principal Components: Intrinsic Dimensionality
      7. 2.7 Neural Networks and Discrete Choice
      8. 2.8 The Black Box Criticism and Data Mining
      9. 2.9 Conclusion
    2. Chapter 3: Estimation of a Network with Evolutionary Computation
      1. 3.1 Data Preprocessing
      2. 3.2 The Nonlinear Estimation Problem
      3. 3.3 Repeated Estimation and Thick Models
      4. 3.4 MATLAB Examples: Numerical Optimization and Network Performance
      5. 3.5 Conclusion
    3. Chapter 4: Evaluation of Network Estimation
      1. 4.1 In-Sample Criteria
      2. 4.2 Out-of-Sample Criteria
      3. 4.3 Interpretive Criteria and Significance of Results
      4. 4.4 Implementation Strategy
      5. 4.5 Conclusion
  8. II: Applications and Examples
    1. Chapter 5: Estimating and Forecasting with Artificial Data
      1. 5.1 Introduction
      2. 5.2 Stochastic Chaos Model
      3. 5.3 Stochastic Volatility/Jump Diffusion Model
      4. 5.4 The Markov Regime Switching Model
      5. 5.5 Volatility Regime Switching Model
      6. 5.6 Distorted Long-Memory Model
      7. 5.7 Black-Sholes Option Pricing Model: Implied Volatility Forecasting
      8. 5.8 Conclusion
    2. Chapter 6: Times Series: Examples from Industry and Finance
      1. 6.1 Forecasting Production in the Automotive Industry
      2. 6.2 Corporate Bonds: Which Factors Determine the Spreads?
      3. 6.3 Conclusion
    3. Chapter 7: Inflation and Deflation: Hong Kong and Japan
      1. 7.1 Hong Kong
      2. 7.2 Japan
      3. 7.3 Conclusion
    4. Chapter 8: Classification: Credit Card Default and Bank Failures
      1. 8.1 Credit Card Risk
      2. 8.2 Banking Intervention
      3. 8.3 Conclusion
    5. Chapter 9: Dimensionality Reduction and Implied Volatility Forecasting
      1. 9.1 Hong Kong
      2. 9.2 United States
      3. 9.3 Conclusion
  9. Bibliography
  10. Index

Product information

  • Title: Neural Networks in Finance
  • Author(s): Paul D. McNelis
  • Release date: December 2004
  • Publisher(s): Academic Press
  • ISBN: 9780124859678