CONTENTS
Foreword by Gregory Piatetsky-Shapiro = xi
Preface = xiii
Acknowledgments = xv
1. The Scope and Methods of the Study
1.1. Introduction = 1
1.2. Problem definition = 3
1.3. Data mining methodologies = 4
1.3.1. Parameters = 4
1.3.2. Problem ID and profile = 6
1.3.3. Comparison of intelligent decision support methods = 7
1.4. Modern methodologies in financial knowledge discovery = 9
1.4.1. Deterministic dynamic system approach = 9
1.4.2. Efficient market theory = 10
1.4.3. Fundamental and technical analyses = 11
1.5. Data mining and database management = 12
1.6. Data mining: definitions and practice = 14
1.7. Learning paradigms for data mining = 17
1.8. Intellectual challenges in data mining = 19
2. Numerical data Mining Models with Financial Applications
2.1. Statistical, autoregression models = 21
2.1.1. ARIMA models = 22
2.1.2. Steps in developing ARIMA model = 25
2.1.3. Seasonal ARIMA = 27
2.1.4. Exponential smoothing and trading day regression = 28
2.1.5. Comparison with other methods = 28
2.2. Financial applications of autoregression models = 30
2.3. Instance―based learning and financial applications = 32
2.4. Neural networks = 36
2.4.1. Introduction = 36
2.4.2. Steps = 38
2.4.3. Recurrent networks = 39
2.4.4. Dynamically modifying network structure = 40
2.5. Neural networks and hybrid systems in finance = 40
2.6. Recurrent neural networks in finance = 42
2.7. Modular networks and genetic algorithms = 44
2.7.1. Mixture of neural networks = 44
2.7.2. Genetic algorithms for modular neural networks = 45
2.8. Testing results and the complete round robin method = 47
2.8.1. Introduction = 47
2.8.2. Approach and method = 47
2.8.3. Multithreaded implementation = 52
2.8.4. Experiments with SP500 and neural networks = 54
2.9. Expert mining = 58
2.10. Interactive Learning of monotone Boolean functions = 66
2.10.1. Basic definitions and results = 66
2.10.2. Algorithm for restoring a monotone Boolean function = 67
2.10.3 Construction of Hansel chains = 69
3. Rule-Based and Hybrid financial Data Mining
3.1. Decision tree and DNF learning = 71
3.1.1. Advantages = 71
3.1.2. Limitation: size of the tree = 72
3.1.3. Constructing decision trees = 81
3.1.4. Ensembles and hybrid methods for decision trees = 84
3.1.5. Discussion = 87
3.2 Decision tree and DNF learning in finance = 88
3.2.1. Decision-tree methods in finance = 88
3.2.2. Extracting decision tree and sets of rules for SP500 = 89
3.2.3. Sets of decision trees and DNF learning in finance = 93
3.3. Extracting decision trees from neural networks = 95
3.3.1. Approach = 95
3.3.2. Trepan algorithm = 96
3.4. Extracting decision trees from neural networks in finance = 97
3.4.1. Predicting the Dollar-Mark exchange rate = 97
3.4.2. Comparison of performance = 99
3.5. Probabilistic rules and knowledge-based stochastic modeling = 102
3.5.1. Probabilistic networks and probabilistic rules = 103
3.5.2. The na i ·· ve Bayes classifier = 106
3.5.3. The mixture of experts = 107
3.5.4. The hidden Markov model = 108
3.5.5. Uncertainty of the structure of stochastic models = 111
3.6. Knowledge-based stochastic modeling in finance = 112
3.6.1. Markov chains in finance = 112
3.6.2. Hidden Markov models in finance = 114
4. Relational Data Mining (RDM)
4.1. Introduction = 115
4.2. Examples = 118
4.3. Relational data mining paradigm = 123
4.4. Challenges and obstacles in relational data mining = 127
4.5. Theory of RDM = 129
4.5.1. Data types in relational data mining = 129
4.5.2. Relational representation of examples = 130
4.5.3. First-order logic and rules = 135
4.6. Background knowledge = 140
4.6.1. Arguments constraints and skipping useless hypotheses = 140
4.6.2. Initial rules and improving search of hypotheses = 141
4.6.3. Relational data mining and relational databases = 144
4.7. Algorithms: FOIL and FOCL = 146
4.7.1. Introduction = 146
4.7.2. FOIL = 147
4.7.3. FOCL = 150
4.8. Algorithm MMDR = 151
4.8.1. Approach = 151
4.8.2. MMDR algorithm and existence theorem = 154
4.8.3. Fisher test = 159
4.8.4. MMDR pseudocode = 162
4.8.5. Comparison of FOIL and MMDR = 165
4.9. Numerical relational data mining = 166
4.10. Data types = 169
4.10.1. Problem of data types = 169
4.10.2. Numerical data type = 174
4.10.3. Representative measurement theory = 174
4.10.4. Critical analysis of data types in ABL = 175
4.11. Empirical axiomatic theories: empirical contents of data = 179
4.11.1. Definitions = 179
4.11.2. Representation of data types in empirical axiomatic theories = 181
4.11.3. Discovering empirical regularities as universal formulas = 186
5. Financial Applications of Relational Data Mining
5.1. Introduction = 189
5.2. Transforming numeric data into relations = 191
5.3. Hypotheses and probabilistic "laws" = 193
5.4. Markov chains as probabilistic "laws" in finance = 196
5.5. Learning = 199
5.6. Method of forecasting = 202
5.7. Experiment 1 = 204
5.7.1. Forecasting Performance for hypotheses H1-H4 = 204
5.7.2. Forecasting Performance for a specific regularity = 207
5.7.3. Forecasting Performance for Markovian expressions = 209
5.8. Experiment 2 = 212
5.9. Interval stock forecast for portfolio selection = 213
5.10. Predicate invention for financial applications: calendar effects = 215
5.11. Conclusion = 218
6. Comparison of Performance of RDM and other methods in financial applications
6.1 Forecasting methods = 219
6.2. Approach: measures of performance = 220
6.3. Experiment 1: simulated trading performance = 222
6.4. Experiment 1: comparison with ARIMA = 225
6.5. Experiment 2: forecast and simulated gain = 227
6.6. Experiment 2: analysis of performance = 227
6.7. Conclusion = 229
7. Fuzzy logic approach and its financial applications
7.1. Knowledge discovery and fuzzy logic = 231
7.2. "Human logic" and mathematical principles of uncertainty = 235
7.3. difference between fuzzy logic and probability theory = 239
7.4. Basic concepts of fuzzy logic = 240
7.5. Inference problems and solutions = 248
7.6. Constructing coordinated contextual linguistic variables = 262
7.6.1. Examples = 252
7.6.2. Context space = 259
7.6.3. Acquisition of fuzzy sets and membership function = 262
7.6.4. Obtaining linguistic variables = 265
7.7. Constructing coordinated fuzzy inference = 266
7.7.1. Approach = 266
7.7.2. Example = 268
7.7.3. Advantages of "exact complete" context for fuzzy inference = 270
7.8. Fuzzy logic in finance = 278
7.8.1. Review of applications of fuzzy logic in finance = 278
7.8.2. Fuzzy logic and technical analysis = 281
REFERENCES = 285
Subject Index = 299
