Questo libro presenta al lettore numerosi metodi d’avanguardia per l’analisi dei mercati e lo sviluppo dei sistemi automatici di trading. Diviso in cinque sezioni, Cybernetic Strategies affronta dapprima le metodologie dell’analisi tecnica classica (intermarket, cicli, stagionalità) e insegna come mettere in opera strategie di analisi molto rigorose e precise. La seconda parte copre svariate metodologie statistiche e matematiche fino ad arrivare all’intelligenza artificiale applicata al trading tramite il System feedback, che consente al sistema di imparare dai propri errori.
La terza parte illustra come formalizzare e automatizzare i metodi soggettivi d’analisi come la Teoria di Elliott e i candlestick. La quarta parte è dedicata alla progettazione, allo sviluppo e al testing dei trading system. La quinta ed ultima sezione illustra come utilizzare diversi metodi derivati dall’intelligenza artificiale per costruire sistemi basati su reti neurali e algoritmi genetici.
Indice dei contenuti
PART ONE
CLASSICAL MARKET PREDICTION
Classical Intermarket Analysis as a Predictive Tool 9
What Is Intermarket Analysis? 9
Using Intermarket Analysis to Develop Filters and Systems 27
Using Intermarket Divergence to Trade the S&P500 29
Predicting T-Bonds with Intermarket Divergence 32
Predicting Gold Using Intermarket Analysis 35
Using Intermarket Divergence to Predict Crude 36
Predicting the Yen with T-Bonds 38
Using Intermarket Analysis on Stocks 39
Seasonal Trading 42
Types of Fundamental Forces 42
Calculating Seasonal Effects 43
Measuring Seasonal Forces 43
The Ruggiero/Barna Seasonal Index 45
Static and Dynamic Seasonal Trading 45
Judging the Reliability of a Seasonal Pattern 46
Counterseasonal Trading 47
Conditional Seasonal Trading 47
Other Measurements for Seasonality 48
Best Long and Short Days of Week in Month 49
Trading Day-of-Month Analysis 51
Day-of-Year Seasonality 52
Using Seasonality in Mechanical Trading Systems 53
Counterseasonal Trading 55
Long-Term Patterns and Market Timing for Interest Rates and Stocks 60
Inflation and Interest Rates 60
Predicting Interest Rates Using Inflation 62
Fundamental Economic Data for Predicting Interest Rates 63
A Fundamental Stock Market Timing Model 68
Trading Using Technical Analysis 70
Why Is Technical Analysis Unjustly Criticized?
70 Profitable Methods Based on Technical Analysis 73
The Commitment of Traders Report 86
What Is the Commitment of Traders Report?
86 How Do Commercial Traders Work? 87
Using the COT Data to Develop Trading Systems 87
PART TWO
STATISTICALLY BASED MARKET PREDICTION
A Trader's Guide to Statistical Analysis 95
Mean, Median, and Mode 96
Types of Distributions and Their Properties 96
The Concept of Variance and Standard Deviation 98
How Gaussian Distribution, Mean, and Standard Deviation Interrelate 98
Statistical Tests' Value to Trading System Developers 99
Correlation Analysis 101
Cycle-Based Trading 103
The Nature of Cycles 105
Cycle-Based Trading in the Real World 108
Using Cycles to Detect When a Market Is Trending 109
Adaptive Channel Breakout 114
Using Predictions from MEM for Trading 115
Combining Statistics and Intermarket Analysis 119
Using Correlation to Filter Intermarket Patterns 119
Predictive Correlation 123
Using the CRB and Predictive Correlation to Predict Gold 124
Intermarket Analysis and Predicting the Existence of a Trend 126
Using Statistical Analysis to Develop Intelligent Exits 130
The Difference between Developing Entries and Exits 130
Developing Dollar-Based Stops 131
Using Scatter Charts of Adverse Movement to Develop Stops 132
Adaptive Stops 137
Using System Feedback to Improve Trading System Performance 140
How Feedback Can Help Mechanical Trading Systems 140
How to Measure System Performance for Use as Feedback 141
Methods of Viewing Trading Performance for Use as Feedback 141
Walk Forward Equity Feedback 142
How to Use Feedback to Develop Adaptive Systems or Switch between Systems 147
Why Do These Methods Work? 147
An Overview of Advanced Technologies 149
The Basics of Neural Networks 149
Machine Induction Methods 153
Genetic Algorithms-An Overview 160
Developing the Chromosomes 161
Evaluating
Fitness 162
Initializing the Population 163
The Evolution 163
Updating a Population 168
Chaos Theory 168
Statistical Pattern Recognition 171
Fuzzy Logic 172
PART THREE
MAKING SUBJECTIVE METHODS MECHANICAL
How to Make Subjective Methods Mechanical 179
Totally Visual Patterns Recognition 180
Subjective Methods Definition Using Fuzzy Logic 180
Human-Aided Sernimechanical Methods 180
Mechanically Definable Methods 183
Mechanizing Subjective Methods 183
Building the Wave 184
An Overview of Elliott Wave Analysis 184
Types of Five-Wave Patterns 186
Using the Elliott Wave Oscillator to Identify the Wave Count 187
TradeStation Tools for Counting Elliott Waves 188
Examples of Elliott Wave Sequences Using Advanced GET 194
Mechanically Identifying and Testing Candlestick Patterns 197
How Fuzzy Logic Jumps Over the Candlestick 197
Fuzzy Primitives for Candlesticks 199 Developing a Candlestick Recognition Utility Step-by-Step 200
PART FOUR
TRADING SYSTEM DEVELOPMENT AND TESTING
Developing a Trading System 209
Steps for Developing a Trading System 209
Selecting a Market for Trading 209
Developing a Premise 211
Developing Data Sets 211
Selecting Methods for Developing a Trading System 212
Designing Entries 214
Developing Filters for Entry Rules 215
Designing Exits 216
Parameter Selection and Optimization 217
Understanding the System Testing and Development Cycle 217
Designing an Actual System 218
Testing, Evaluating, and Trading a Mechanical Trading System 225
The Steps for Testing and Evaluating a Trading System 226
Testing a Real Trading System 231
PART FIVE USING ADVANCED TECHNOLOGIES TO DEVELOP TRADING STRATEGIES
Data Preprocessing and Postprocessing 241 Developing Good Preprocessing-An Overview 241
Selecting a Modeling Method 243
The Life Span of a Model 243
Developing Target Output(s) for a Neural Network 244
Selecting Raw Inputs 248
Developing Data Transforms 249
Evaluating Data Transforms 254
Data Sampling 257
Developing Development, Testing, and Out-of-Sample Sets 257
Data Postprocessing 258
Developing a Neural Network Based on Standard Rule-Based Systems 259
A Neural Network Based on an Existing Trading System 259
Developing a Working Example Step-by-Step 264
Machine Learning Methods for Developing Trading Strategies 280
Using Machine Induction for Developing Trading Rules 281
Extracting Rules from a Neural Network 283
Combining Trading Strategies 284
Postprocessing a Neural Network 285
Variable Elimination Using Machine Induction 286
Evaluating the Reliability of Machine-Generated Rules 287
Using Genetic Algorithms for Trading Applications 290
Uses of Genetic Algorithms in Trading 290
Developing Trading Rules Using a Genetic Algorithm-An Example 293
|
