You are previewing Business Intelligence in Economic Forecasting: Technologies and Techniques.
O'Reilly logo
Business Intelligence in Economic Forecasting: Technologies and Techniques

Book Description

Business Intelligence in Economic Forecasting: Technologies and Techniques discusses various Business Intelligence techniques including neural networks, support vector machine, genetic programming, clustering analysis, TEI@I, fuzzy systems, text mining, and many more. This publication serves as a valuable reference for professionals and researchers interested in BI technologies and their practical applications in economic forecasting, as well as policy makers in business organizations and governments.

Table of Contents

  1. Copyright
  2. Editorial Advisory Board
  3. List of Reviewers
  4. Foreword
  5. Preface
    1. SECTION 1: BI IN MACRO-ECONOMIC ANALYSIS AND FORECASTING
    2. SECTION 2: BI IN FINANCIAL MARKETS ANALYSIS AND FORECASTING
    3. SECTION 3: BI IN INDUSTRIES ANALYSIS AND FORECASTING
  6. 1. BI in Macro-Economic Analysis and Forecasting
    1. 1. Macroeconomic Forecasting Using Genetic Programming Based Vector Error Correction Model
      1. ABSTRACT
      2. 1. INTRODUCTION
        1. 1.1 Overview of the Development of Macroeconomic Forecasting
        2. 1.2 Motivation of Our Work
      3. 2. BACKGROUND KNOWLEDGE
        1. 2.1 Genetic Programming
        2. 2.2 Vector Error Correction Model
      4. 3. OUR HYBRID MODEL
      5. 4. EMPIRICAL STUDY
        1. 4.1 Data
        2. 4.2 Results
      6. 5. CONCLUSION
      7. ACKNOWLEDGMENT
      8. REFERENCES
      9. KEY TERMS AND DEFINITIONS
    2. A. APPENDIX
      1. A. Fitness Evaluating Process
      2. B. Flowchart of Fitness Evaluation
    3. 2. Economic Forecasting Techniques and Their Applications
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. LITERATURE REVIEW ON FORECASTING
        1. 2.1. Forecasting Using Neural Networks
        2. 2.2. Forecasting Using Grey Theory
        3. 2.3. Forecasting Using Fuzzy Set Theory
        4. 2.4. Forecasting Using Genetic Algorithms
        5. 2.5. Forecasting Using Integrated Techniques
      4. 3. ECONOMIC FORECASTING TECHNIQUES
        1. 3.1. Forecasting by Regression
          1. 3.1.1. Estimation in Simple Linear Regression
          2. 3.1.2. Estimation in Fuzzy Simple Linear Regression
        2. 3.2. Forecasting by Time Series
          1. 3.2.1. Smoothing Methods
            1. 3.2.1.1. Moving Averages
            2. 3.2.1.2. Exponential Smoothing
            3. 3.2.1.3. Seasonal Time Series
        3. 3.2.2. Fuzzy Logic Methods
      5. 3.3. Grey Theory
        1. 3.3.1. Grey Forecasting Model
        2. 3.4. The Delphi Method
        3. 3.5. Nominal Group Technique
      6. 4. APPLICATIONS
        1. 4.1. Forecasting Cash Flows Using Fuzzy Time Series
        2. 4.2. Forecasting Interest Rates using Fuzzy Time Series
        3. 4.3. Forecasting cash Flows using grey Model
        4. 4.4. Forecasting Interest Rates using grey Model
        5. 4.5. calculation of Fuzzy Present Worth
        6. 4.6. Forecasting for Simple Linear Regression
        7. 4.7. Fuzzy Prediction for Simple Linear Regression
      7. 5. CONCLUSION
      8. REFERENCES
      9. KEY TERMS AND DEFINITIONS
    4. 3. Logistic Analysis of Business Cycles, Economic Bubbles and Crises
      1. ABSTRACT
      2. INTRODUCTION
      3. ECONOMIC GROWTH AND BUSINESS CYCLES
      4. LOGISTIC GROWTH
        1. Logistic Growth Model
        2. Logistic Evaluation of Investments Based on Internal Rate of Return
        3. Debt Trap
        4. Case Study
      5. FURTHER RESEARCH DIRECTIONS
      6. CONCLUSION
      7. REFERENCES
      8. ADDITIONAL READING
      9. KEY TERMS AND DEFINITIONS
    5. 4. A Visualization and Clustering Approach to Analyzing the Early Warning Signals of Currency Crises
      1. ABSTRACT
      2. INTRODUCTION
      3. FINANCIAL CRISIS AND EARLY WARNING SYSTEMS
      4. SELF-ORGANIZING MAPS
      5. ANALYZING THE FINNISH CURRENCY CRISIS USING THE SOM
        1. Selection of Early Warning Indicators
        2. The Data
        3. SOM Analysis
      6. CONCLUSIONS AND FUTURE TRENDS
      7. ACKNOWLEDGMENT
      8. REFERENCES
      9. ADDITIONAL READING
      10. KEY TERMS AND DEFINITIONS
    6. 5. Economic Analysis of Systems Under a Monopoly Based on a Reliability-Quality Index
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. BACKGROUND
        1. 2.1. System Planning Process and Economic Analysis
        2. 2.2 Forecasting Techniques for System Planning
        3. 2.3. Optimization Techniques for System Planning
      4. 3. GAME THEORY APPROACH IN THE ECONOMIC ANALYSIS OF SYSTEMS
        1. 3.1. Fundamental Approach toward System Comparison
        2. 3.2. System Comparison with Design Variable Optimization
        3. 3.3. Numerical Examples
      5. 4. ECONOMIC ANALYSES OF PARALLEL REDUNDANT SYSTEMS AGAINST A SINGLE UNIT SYSTEM
        1. 4.1. Mathematical Formulation
        2. 4.2 Numerical Examples
      6. 5. ECONOMIC ANALYSIS OF MULITIPLE PARALLEL REDUNDANT SYSTEMS
        1. 5.1. Mathematical Formulation
        2. 5.2. Numerical Examples
      7. 6. CONCLUSION AND FUTURE WORKS
      8. REFERENCES
      9. KEY TERMS AND DEFINITIONS
  7. 2. BI in Financial Markets Analysis and Forecasting
    1. 6. A Confidence-Based RBF Neural Network Ensemble Learning Paradigm with Application to Delinquent Prediction for Credit Risk Management
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. FORMULATION OF THE CONFIDENCE-BASED RBF NEURAL NETWORK ENSEMBLE APPROACH
        1. 2.1. Partitioning Original Data Set
        2. 2.2. Creating Single RBF Neural Network Ensemble Members
        3. 2.3. Training RBF Neural Network and Generating Confidence Value
        4. 2.4. Transforming Confidence Value
        5. 2.5. Fusing Multiple Prediction Results into an Ensemble Output
      4. 3. EXPERIMENTS
        1. 3.1. Dataset I: Corporate Credit Case
        2. 3.2. Dataset II: Consumer Credit Case
      5. 4. CONCLUSION
      6. ACKNOWLEDGMENT
      7. REFERENCES
    2. 7. Empirical Evaluation of Ensemble Learning for Credit Scoring
      1. ABSTRACT
      2. INTRODUCTION
      3. RELATED WORK
        1. Traditional Statistical Techniques for Credit Scoring
        2. AI Techniques for Credit Scoring
      4. ENSEMBLE LEARNING FOR CREDIT SCORING
        1. Overviews of Ensemble Learning
        2. Bagging
        3. Boosting
        4. Stacking
      5. EXPERIMENTAL DESIGN
        1. Real World Credit Dataset
        2. Evaluation Criteria
        3. Experimental Procedure
      6. RESULTS AND ANALYSES
      7. CONCLUSION AND FUTURE DIRECTIONS
      8. ACKNOWLEDGMENT
      9. REFERENCES
      10. KEY TERMS AND DEFINITIONS
    3. 8. Bankruptcy Prediction Using Principal Component Analysis Based Neural Network Models
      1. ABSTRACT
      2. INTRODUCTION
      3. PRINCIPAL COMPONENT ANALYSIS: A BRIEF NOTE
      4. ROC ANALYSIS: A QUICK TOUR
      5. ARCHITECTURES AND LEARNING RULES OF THE NEURAL NETWORK MODELS
        1. Backpropagation Neural Network With Levenberg Marquardt's Training Rule
        2. Evolutionary Neural Network
      6. DATA PREPARATION AND PROCESSING
      7. EXPERIMENTAL RESULTS OF THE PCA-ENN AND PCA-BPN MODELS
        1. PCA-ENN Model (Isolated Database)
        2. PCA-ENN Model (Non Isolated Database)
        3. PCA-BPN Model (Isolated Database)
        4. PCA-BPN Model (Non Isolated Database)
        5. Salient Features of the PCA-ENN and PCA-BPN Prediction Models
      8. PERFORMANCE COMPARISON OF THE PCA-ENN AND PCA-BPN PREDICTION MODELS
      9. FUTURE RESEARCH DIRECTIONS
      10. CONCLUSION
      11. REFERENCES
      12. KEY TERMS AND DEFINITIONS
    4. 9. A Mixture Price Trend Model for Long-Term Risk Management
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND ON PRICE TREND MODELS
      4. TAYLOR'S PRICE TREND MODEL
      5. A MIXTURE PRICE TREND MODEL
      6. ESTIMATION
        1. The Bi-Level Bayesian Recursive Procedure for Hidden Variables
        2. Maximum Likelihood Estimation of Model Parameters
      7. RISK MEASURES: VAR AND ES
        1. ES and VaR of Financial instruments
      8. EMPIRICAL RESULTS AND COMPARISON
      9. FUTURE RESEARCH DIRECTIONS
      10. CONCLUSION
      11. ACKNOWLEDGMENT
      12. REFERENCES
      13. ADDITIONAL READING
      14. KEY TERMS AND DEFINITIONS
    5. 10. Increasing Translation Invariant Morphological Forecasting Models for Stock Market Prediction
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. BACKGROUND
        1. 2.1 Time Series Forecasting Problem
        2. 2.2 The Random Walk Dilemma
        3. 2.3 Linear Statistical Models
          1. 2.3.1 Box and Jenkins Models
        4. 2.4 Nonlinear Statistical Models
        5. 2.5 Neural Network Models
          1. 2.5.1 Multilayer Perceptron Neural Network
        6. 2.6 Genetic Algorithms
          1. 2.6.1 Standard Genetic Algorithm
          2. 2.6.2 Modified Genetic Algorithm
        7. 2.7 intelligent Hybrid Models
          1. 2.7.1 TAEF Model
      4. 3. MATHEMATICAL MORPHOLOGY
        1. 3.1. Matheron Decomposition Theorem
        2. 3.2. Modular Morphological Neural Network (MMNN) Preliminaries
        3. 3.3. MMNN Definition
        4. 3.4. MMNN training Algorithm
      5. 4. MAIN FOCUS OF THE CHAPTER
        1. 4.1 Performance Metrics
        2. 4.2 Simulations and Experimental Results
          1. 4.2.1 Dow Jones Industrial Average (DJIA) Index Series
          2. 4.2.2 Standard & Poor 500 (S&P500) Index Series
          3. 4.2.3 AT&T Inc Stock Prices Series
          4. 4.2.4 Apple Inc Stock Prices Series
      6. 5. FUTURE RESEARCH DIRECTIONS
      7. 6. CONCLUSION
      8. REFERENCES
      9. KEY TERMS AND DEFINITIONS
    6. 11. On the Efficient Dynamical Financial Analysis Computation Supported by UML(VR)
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. DYNAMIC FINANCIAL ANALYSIS OVERVIEW
        1. DFA Implementation Issues
        2. Multi–Scenario Related Problems
      5. DESCRIPTION OF SOFTWARE SYSTEM ARCHITECTURE
        1. Introduction to UML
        2. UML(VR) Concept
        3. Structure of DFA Processes
        4. Description of Single DFA Process
        5. Hardware Environment Description
        6. Estimation of Process Characteristic: Timing Diagrams for Single Process
      6. ALLOCATION OF A NEW DFA PROCESS
        1. Basic Properties of the Parallel Graph Transformation System
          1. Definition 1
          2. Definition 2
        2. The DFA Process Description and the Optimal Deployment Method
      7. FUTURE RESEARCH DIRECTIONS
      8. CONCLUSION
      9. REFERENCES
      10. ADDITIONAL READING
      11. KEY TERMS
  8. 3. BI in Industries Analysis and Forecasting
    1. 12. Forecasting Crude Oil Demand Using a Hybrid SVR and Markov Approach
      1. ABSTRACT
      2. INTRODUCTION
      3. A HYBRID SVR AND MARKOV FORECASTING APPROACH
        1. An SVR-Based Forecasting Method
        2. A Hybrid SVR and Markov Forecasting Approach
      4. FORECAST OF WORLD CRUDE OIL DEMAND
        1. Data Preprocessing
        2. Training
        3. Testing
        4. Forecasting World Crude oil Demand
      5. EVALUATION AND COMPARISON
        1. Data Description and Evaluation Criteria
        2. Experimental results
      6. CONCLUSION
      7. ACKNOWLEDGMENT
      8. REFERENCES
      9. KEY TERMS AND DEFINITIONS
    2. 13. Analysis and Forecasting of Port Logistics Using TEI@I Methodology
      1. ABSTRACT
      2. INTRODUCTION
      3. THE TEI@I FORECASTING FRAMWORK AS A PORT LOGISTICS FORECASTING TOOL
        1. (1) S-ARIMA Model
        2. (2)VAR Model
        3. (3)RBF Neural Network
      4. HONG KONG PORT CONTAINER THROUGHPUT FORECASTING: A CASE STUDY
        1. Data Description and Evaluation Criteria
        2. Empirical Results
      5. CONCLUSION
      6. REFERENCES
      7. KEY TERMS AND DEFINITIONS
    3. 14. Time Series Based House Sale Value Market Forecasting Using Genetically Evolved Neural Networks
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. MAIN FOCUS OF THE CHAPTER
        1. Problem Statement
        2. Linear Regression Model
        3. Adaptive Neuro Fuzzy Inference System (ANFIS)
        4. Hybrid Genetically Evolved ANN Model
      5. SOLUTIONS AND RECOMMENDATIONS
      6. FUTURE DIRECTIONS
      7. CONCLUSION
      8. REFERENCES
      9. ADDITIONAL READING
      10. KEY TERMS AND DEFINITIONS
    4. 15. Implementing Business Intelligence in Electricity Markets
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
        1. Business Intelligence: Foundations, Advantages and Limits
        2. High Frequency Data: A New Source to Increase Managerial Intelligence
        3. Searching for Adequate Tools: The role of time Series Models
      4. BUSINESS INTELLIGENCE IN ELECTRICITY MARKETS: A CASE STUDY
        1. Market Participants and Their Needs
        2. Time Series Models for High Frequency data of electricity consumption
        3. Meeting the Needs of a Particular organization
      5. FUTURE RESEARCH DIRECTIONS AND CONCLUSION
      6. ACKNOWLEDGMENT
      7. REFERENCES
      8. KEY TERMS AND DEFINITIONS
    5. 16. Electricity Demand Forecasting
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. ELECTRICITY LOAD FORECASTING METHODOLOGIES
        1. 2.1. General
        2. 2.2. Characteristics of Load Forecasting Model
        3. 2.3. Forecasting Perspectives
          1. 2.3.1. Descriptive vs. Quantitative
          2. 2.3.2. Global vs. Disaggregated
          3. 2.3.3. Projective vs. Normative
        4. 2.4. Forecasting Steering Factors
          1. 2.4.1. State of the Economy
          2. 2.4.2. Clear Vision
          3. 2.4.3. Type of Economy
          4. 2.4.4. Status of the Electric Power System
          5. 2.4.5. Status of Electricity Market
          6. 2.4.6. Understanding of the Interrelations With Other Energy Forms
          7. 2.4.7. Integrating Other Demand Manipulation Programs in the Forecasting
      4. 3. ELECTRICITY FORECASTING MODELS AND TECHNIQUES
        1. 3.1. Statistical-Based Methods
          1. 3.1.1. Regression Methods
            1. A. Simple Linear Regression
            2. B. The Polynomial Regression
            3. C.A Selected Model-Function Regression
            4. D.Multiple Regression
          2. 3.1.2. Time Series
          3. 3.1.3. Similar-Day Approach
          4. 3.1.4 Econometric or Causal Method
          5. 3.1.5. Simulation or End-Use Methods
        2. 3.2 Artificial Intelligence (AI)-Based Methods
          1. 3.2.1. Neural Networks
          2. 3.2.2. Expert Systems
          3. 3.2.3. Fuzzy Logic Systems
          4. 3.2.4. Support Vector Machines (SVM)
          5. 3.2.5. The Particle Swarm Optimization (PSO) Algorithm
        3. 3.3. Electrical Forecasting Time Frames
          1. 3.3.1. Short-Term and Very Short-Term Forecasting Models
          2. 3.3.2. Medium-Term Forecasting Models
          3. 3.3.3. Long-Term Forecasting Models
      5. 4. CASE STUDIES OF ELECTRICITY FORECASTING IN JORDAN
        1. 4.1 Case 1: Short-Term Load Forecasting
        2. 4.2. Case 2: Long Term Load Forecasting
      6. CONCLUSION
      7. FUTURE RESEARCH DIRECTIONS
      8. REFERENCES
      9. KEY TERMS AND DEFINITIONS
    6. 17. Electricity Load Forecasting Using Machine Learning Techniques
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
        1. Support Vector Machines for Electricity Load Forecasting
        2. Non-Linear Support Vector Machines
        3. Kernel SVM
      4. SVM-SOM: A NEW LOCAL MODEL FOR ELECTRICITY LOAD FORECASTING
        1. The Self Organizing Maps
        2. A SOM Algorithm to Segment the Load Time Series
      5. MAXIMUM ELECTRICITY LOAD FORECASTING: CASE STUDY
        1. Temperature
        2. Day of the Week and Season
        3. Electricity Load Demand for Previous Days
      6. EXPERIMENTAL RESULTS
      7. FUTURE RESEARCH DIRECTIONS
      8. CONCLUSION
      9. REFERENCES
      10. KEY TERMS AND DEFINITIONS
  9. Compilation of References
  10. About the Contributors