You are previewing Artificial Higher Order Neural Networks for Economics and Business.
O'Reilly logo
Artificial Higher Order Neural Networks for Economics and Business

Book Description

Artificial Higher Order Neural Networks for Economics and Business is the first book to provide practical education and applications for the millions of professionals working in economics, accounting, finance and other business areas on HONNs and the ease of their usage to obtain more accurate application results.

Table of Contents

  1. Copyright
  2. Dedication
  3. Preface
  4. Acknowledgment
  5. Artificial Higher Order Neural Networks for Economics
    1. Artificial Higher Order Neural Network Nonlinear Models: SAS NLIN or HONNs?
      1. ABSTRACT
      2. INTRODUCTION
      3. SAS
      4. HONN STRUCTURE AND NONLINEAR MODLES
      5. CONVERGENCE THEORIES OF HONN
      6. LEARNING ALGORITHM OF HONN MODEL
      7. HONN NONLINEAR MODELS
      8. SINCHONN
      9. SPHONN
      10. COMPARISONS OF SAS NONLINEAR MODELS AND HONN NONLINEAR MODELS
      11. FINDING MODEL, ORDER, & COEFFICIENT BY HONN NONLINEAR MODELS
      12. FUTHER RESEARCH DIRECTIONS
      13. CONCLUSION
      14. ACKNOWLEDGMENT
      15. REFERENCES
      16. ADDITIONAL READING
    2. APPENDICES
      1. Appendix A: Output Neurons in HONN Model (model 0, 1, and 1b)
      2. Appendix B: Second-Hidden Layer Neurons in HONN Model (Model 1b)
      3. Appendix C: First Hidden Layer Neurons in HONN (Model 1 and Model 1b)
    3. Higher Order Neural Networks with Bayesian Confidence Measure for the Prediction of the EUR/USD Exchange Rate
      1. ABSTRACT
      2. INTRODUCTION
      3. METHODS AND MODELS
      4. SIMULATION
      5. DISCUSSION
      6. CONCLUSION
      7. FUTURE RESEARCH DIRECTIONS
      8. REFERENCES
      9. ADDITIONAL READING
      10. ENDNOTE
    4. Automatically Identifying Predictor Variables for Stock Return Prediction
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. LEARNING ENVIRONMENT
      5. PREDICTOR VARIABLES SELECTION ALGORITHM
      6. EXPERIMENTAL RESULTS
      7. CONCLUSION
      8. FUTURE RESEARCH DIRECTIONS
      9. REFERENCES
      10. ADDITIONAL READING
    5. APPENDIX A
    6. Higher Order Neural Network Architectures for Agent-Based Computational Economics and Finance
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. APPROXIMATE DYNAMIC PROGRAMMING
      5. APPLICATION TO ECONOMIC SYSTEMS
      6. FUTURE RESEARCH DIRECTIONS
      7. REFERENCES
      8. ADDITIONAL READING
    7. Foreign Exchange Rate Forecasting Using Higher Order Flexible Neural Tree
      1. ABSTRACT
      2. INTRODUCTION
      3. HIGHER ORDER FLEXIBLE NEURAL TREE
      4. GGGP-DRIVEN HOFNT MODEL
      5. GEP-DRIVEN HOFNT MODEL
      6. EXPERIMENT SETUP AND RESULT
      7. CONCLUSION AND FUTURE RESEARCH DIRECTIONS
      8. ACKNOWLEDGMENT
      9. REFERENCES
      10. ADDITIONAL READING
    8. Higher Order Neural Networks for Stock Index Modeling
      1. ABSTRACT
      2. INTRODUCTION
      3. STOCK INDICES FORECASTING
      4. ARTIFICIAL NEURAL NETWORKS (ANNS)
      5. HIGHER ORDER NEURAL NETWORKS (HONNS)
      6. APPLICATION OF HONNS TO FINANCIAL TIME SERIES DATA
      7. CONCLUSION
      8. ACKNOWLEDGMENT
      9. REFERENCES
      10. ADDITIONAL READING
  6. Artificial Higher Order Neural Networks for Time Series Data
    1. Ultra High Frequency Trigonometric Higher Order Neural Networks for Time Series Data Analysis
      1. ABSTRACT
      2. INTRODUCTION
      3. UTHONN MODELS
      4. LEARNING ALGORITHM OF UTHONN MODELS
      5. UTHONN TESTING
      6. COMPARISON OF THONN WITH OTHER HIGHER ORDER NEURAL NETWORKS
      7. COMPARISONS WITH UTHONN AND EQUILIBRIUM REAL EXCHANGE RATES
      8. APPLICATIONS
      9. CONCLUSION
      10. FUTHER RESEARCH DIRECTIONS
      11. ACKNOWLEDGMENT
      12. REFERENCES
      13. ADDITIONAL READING
    2. APPENDIX
      1. First Hidden Layer Neurons in UCS (Model 1 and Model 1b)
    3. Artificial Higher Order Pipeline Recurrent Neural Networks for Financial Time Series Prediction
      1. ABSTRACT
      2. INTRODUCTION
      3. OVERVIEW OF NEURAL NETWORKS
      4. HIGHER-ORDER NEURAL NETWORKS
      5. PIPELINED RECURRENT NEURAL NETWORKS (PRNNS)
      6. SIMULATION RESULTS
      7. CONCLUSION
      8. FUTURE RESEARCH DIRECTIONS
      9. REFERENCES
      10. ADDITIONAL READING
    4. A Novel Recurrent Polynomial Neural Network for Financial Time Series Prediction
      1. ABSTRACT
      2. INTRODUCTION
      3. TIME SERIES ANALYSIS
      4. ARTIFICIAL NEURAL NETWORKS ARCHITECTURES
      5. PERFORMANCE METRICS
      6. SIMULATION RESULTS
      7. IDENTIFICATION OF NARMAX MODEL USING THE RECURRENT PI-SIGMA NEURAL NETWORK
      8. CONCLUSION
      9. FUTURE RESEARCH DIRECTIONS
      10. REFERENCES
      11. ADDITIONAL READING
    5. Generalized Correlation Higher Order Neural Networks for Financial Time Series Prediction
      1. ABSTRACT
      2. INTRODUCTION
      3. EXTENDED CORRELATION MODEL OF NEURAL NETWORKS
      4. DESIGN OF GENERALIZED CORRELATION HIGHER ORDER NEURAL NETWORKS
      5. GENERALIZED CORRELATION HIGHER ORDER NEURAL NETWORK DESIGNS FOR SIMULATION
      6. SIMULATIONS PREDICTING STOCK MARKET SHARE PRICE AND SHARE INDEX
      7. SIMULATIONS PREDICTING INTER-BANK LENDING RISK INTEREST RATE YIELD CURVES
      8. FUTURE RESEARCH DIRECTIONS
      9. REFERENCES
      10. ADDITIONAL READING
    6. Artificial Higher Order Neural Networks in Time Series Prediction
      1. ABSTRACT
      2. BACKGROUND
      3. COMPARISON OF NEURAL NETWORK (NN) AND ARTIFICIAL HIGHER ORDER NEURAL NETWORK (HONN)
      4. POLYNOMIAL NEURAL NETWORK
      5. APPLICATIONS OF THE POLYNOMIAL NEURAL NETWORK
      6. FUTURE RESEARCH DIRECTIONS
      7. CONCLUSION
      8. REFERENCES
      9. ADDITIONAL READING
    7. Application of Pi-Sigma Neural Networks and Ridge Polynomial Neural Networks to Financial Time Series Prediction
      1. ABSTRACT
      2. INTRODUCTION
      3. ARTIFICIAL HIGHER ORDER NEURAL NETWORKS (HONNS)
      4. PI-SIGMA NEURAL NETWORKS (PSNNS)
      5. RIDGE POLYNOMIAL NEURAL NETWORKS (RPNNS)
      6. FINANCIAL TIME SERIES PREDICTION
      7. PERFORMANCE MEASURES
      8. RESULTS
      9. CONCLUSION
      10. FUTURE RESEARCH DIRECTIONS
      11. REFERENCES
      12. ADDITIONAL READING
  7. Artificial Higher Order Neural Networks for Business
    1. Electric Load Demand and Electricity Prices Forecasting Using Higher Order Neural Networks Trained by Kalman Filtering
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. MAIN THRUST OF THE CHAPTER
      5. RESULTS OF SIMULATION
      6. CONCLUSION
      7. FUTURE RESEARCH DIRECTIONS
      8. ACKNOWLEDGMENT
      9. REFERENCES
      10. ADDITIONAL READING
    2. Adaptive Higher Order Neural Network Models and Their Applications in Business
      1. ABSTRACT
      2. INTRODUCTION
      3. ANN STRUCTURE AND LEARNING PROCESS (Dayhoff, 1990; Haykin, 1994; Picton, 2000)
      4. HONNs
      5. ADAPTIVE HONN MODELS
      6. ADAPTIVE HONN MODEL APPLICATIONS IN BUSINESS
      7. CONCLUSION
      8. ACKNOWLEDGMENT
      9. REFERENCES
      10. ADDITIONAL READING
    3. APPENDIX
    4. CEO Tenure and Debt: An Artificial Higher Order Neural Network Approach
      1. ABSTRACT
      2. INTRODUCTION
      3. POLYNOMIAL HIGHER ORDER NEURAL NETWORKS
      4. HYPOTHESES
      5. METHODOLOGY
      6. T-TEST RESULTS AND ANALYSIS
      7. LINEAR MODELS
      8. NONLINEAR MODEL BY USING HONNs
      9. CONCLUSION
      10. FUTURE RESEARCH DIRECTIONS
      11. REFERENCES
      12. ADDITIONAL READING
    5. APPENDIX
    6. Modelling and Trading the Soybean-Oil Crush Spread with Recurrent and Higher Order Networks: A Comparative Analysis
      1. ABSTRACT
      2. INTRODUCTION
      3. LITERATURE REVIEW
      4. DATA AND METHODOLOGY
      5. TRADING MODELS
      6. TRADING FILTERS
      7. RESULTS
      8. CONCLUSION
      9. FUTURE RESEARCH DIRECTIONS
      10. ACKNOWLEDGMENT
      11. REFERENCES
      12. ADDITIONAL READING
      13. ENDNOTES
    7. APPENDIX
  8. Artificial Higher Order Neural Networks Fundamentals
    1. Fundamental Theory of Artificial Higher Order Neural Networks
      1. ABSTRACT
      2. INTRODUCTION
      3. ARTIFICIAL SECOND ORDER NEURAL UNITS AND NETWORKS
      4. PERFORMANCE ASSESSMENT OF ARTIFICIAL SECOND ORDER NEURAL UNITS
      5. ARTIFICIAL HIGHER ORDER NEURAL UNITS AND NETWORKS
      6. TOWARD BUSINESS AND ECONOMIC APPLICATIONS
      7. CONCLUSION AND FUTURE RESEARCH DIRECTIONS
      8. REFERENCES
      9. ADDITIONAL READING
    2. Dynamics in Artificial Higher Order Neural Networks with Delays
      1. ABSTRACT
      2. INTRODUCTION
      3. DYNAMICS OF HIGHER ORDER BAM NEURAL NETWORKS
      4. EXPONENTIAL STABILITY OF HIGHER ORDER BAM NEURAL NETWORKS WITH TIME DELAYS
      5. EXISTENCE OF PERIODIC SOLUTIONS
      6. GLOBAL ASYMPTOTIC STABILITY OF PERIODIC SOLUTION
      7. STABILITY OF HIGHER ORDER BAM NEURAL NETWORKS WITH IMPULSES
      8. FUTURE RESEARCH DIRECTIONS
      9. CONCLUSION
      10. ACKNOWLEDGMENT
      11. REFERENCES
      12. ADDITIONAL READING
    3. A New Topology for Artificial Higher Order Neural Networks: Polynomial Kernel Networks
      1. ABSTRACT
      2. INTRODUCTION
      3. POLYNOMIAL KERNEL NETWORKS
      4. DETERMINING THE OPTIMAL TOPOLOGICAL STRUCTURE OF POLYNOMIAL KERNEL NETWORKS VIA QUADRATIC PROGRAMMING
      5. DETERMINING THE OPTIMAL TOPOLOGICAL STRUCTURE OF POLYNOMIAL KERNEL NETWORKS VIA LINEAR PROGRAMMING
      6. CONCLUSION
      7. FUTURE RESEARCH OUTLOOK
      8. REFERENCES
      9. ADDITIONAL READING
    4. High Speed Optical Higher Order Neural Networks for Discovering Data Trends and Patterns in Very Large Databases
      1. ABSTRACT
      2. INTRODUCTION
      3. OPTICAL WAVEGUIDE CHIP-TO-CHIP INTERCONNECTION TECHNOLOGY
      4. FREE SPACE OPTICAL CORRELATOR HIGHER ORDER NEURAL NETWORKS
      5. FUTURE RESEARCH DIRECTIONS
      6. ACKNOWLEDGMENT
      7. REFERENCES
      8. ADDITIONAL READING
    5. On Complex Artificial Higher Order Neural Networks: Dealing with Stochasticity, Jumps and Delays
      1. ABSTRACT
      2. INTRODUCTION
      3. PROBLEM FORMULATION
      4. MAIN RESULTS AND PROOFS
      5. A NUMERICAL EXAMPLE
      6. CONCLUSION
      7. FUTURE RESEARCH DIRECTIONS
      8. ACKNOWLEDGMENT
      9. REFERENCES
      10. ADDITIONAL READING
    6. Trigonometric Polynomial Higher Order Neural Network Group Models and Weighted Kernel Models for Financial Data Simulation and Prediction
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. TRIGONOMETRIC POPLYNOMIAL HIGHER ORDER NEURAL NETWORK GROUP MODELS
      5. EXPERIMENTAL TESTING OF THE THONG MODELS
      6. FUTURE TRENDS
      7. CONCLUSION
      8. REFERENCES
  9. About the Contributors
  10. Index