Designing stock market trading systems : with and without soft computing / / by Dr. Bruce Vanstone and Tobias Hahn

• Autore: Vanstone Bruce
• Pubblicazione: Petersfield [Great Britain] : , : Harriman House, , 2010
• Descrizione fisica: 1 online resource (xv, 240 p. ) : charts (some col.)
• Disciplina: 262
• Soggetto topico: Stock exchanges; Stock price forecasting; Soft computing; Stocks
• Soggetto genere / forma: Electronic books.
• Altri autori: HahnTobias
• Note generali: Bibliographic Level Mode of Issuance: Monograph
• Nota di bibliografia: Includes bibliographical references and index.
• Nota di contenuto: PrefaceAcknowledgementsIntroduction1. Designing Stock Market Trading Systems1.1 Introduction1.2 Motivation1.3 Scope and Data1.4 The Efficient Market Hypothesis1.5 The Illusion of Knowledge1.6 Investing versus Trading1.6.1 Investing1.6.2 Trading1.7 Building a Mechanical Stock Market Trading System1.8 The Place of Soft Computing1.9 How to Use this Book2. Introduction to Trading2.1 Introduction2.2 Different Approaches to Trading2.2.1 Direction of trading2.2.2 Time frame of trading2.2.3 Type of behaviour exploited2.2.3.1 Trend-based trading2.2.3.2 Breakout trading2.2.3.3 Momentum trading2.2.3.4 Mean reversion trading2.2.3.5 High-frequency trading2.3 Conclusion2.4 The Next Step3. Fundamental Variables3.1 Introduction3.1.1 Benjamin Graham and value investing3.2 Informational Advantage and Market Efficiency3.3 A Note on Adjustments3.4 Core Strategies3.4.1 Intrinsic value estimates3.4.2 Fundamental filters3.4.3 Ranking filters3.5 The elements of a fundamentals-based filter3.5.1 Wealth of a firm and its shareholders3.5.1.1 Book value3.5.1.2 Current assets vs. current liabilities3.5.1.3 Leverage metrics3.5.2 Earnings capacity3.5.3 Ability to generate cash3.6 Fundamental Ratios and Industry Comparisons3.7 A Final Note on Cross-country Investing Research3.8 The Next Step3.9 Case Study: Analysing a Variable3.9.1 Introduction3.9.2 Example - P/E ratio3.9.3 Wealth-Lab3.9.4 SPSS3.9.5 Outliers4. Technical Variables4.1 Introduction4.1.1 Charting4.1.2 Technical indicators4.1.3 Other approaches4.2 Charting and Pattern Analysis4.3 Technical Indicators4.3.1 Intermarket analysis4.3.2 Moving averages4.3.3 Volume4.3.4 Momentum indicators4.3.4.1 Moving Average Convergence/Divergence (MACD)4.3.4.2 Relative Strength Indicator (RSI)4.4 Alternative Approaches4.5 On Use and Misuse of Technical Analysis4.6 Case Study: Does Technical Analysis Have Any Credibility?5. Soft Computing5.1 Introduction5.1.1 Types of soft computing5.1.2 Expert systems5.1.3 Case-based reasoning5.1.4 Genetic algorithms5.1.5 Swarm intelligence5.1.6 Artificial neural networks5.2 Review of Research5.2.1 Soft computing classification5.2.2 Research into time series prediction5.2.3 Research into pattern recognition and classification5.2.4 Research into optimisation5.2.5 Research into ensemble approaches5.3 Conclusion5.4 The Next Step6. Creating Artificial Neural Networks6.1 Introduction6.2 Expressing Your Problem6.3 Partitioning Data6.4 Finding Variables of Influence6.5 ANN Architecture Choices6.6 ANN Training6.6.1 Momentum6.6.2 Training rate6.7 ANN In-sample Testing6.8 Conclusion6.9 The Next Step7. Trading Systems and Distributions7.1 Introduction7.2 Studying a Group of Trades7.2.1 Average profitability metrics7.2.1.1 The students t-test7.2.1.2 The runs test7.2.2 Winning metrics7.2.3 Losing metrics7.2.4 Summary metrics7.2.5 Distributions7.2.5.1 Short-term distribution7.2.5.2 Medium-term distribution7.2.5.3 Long-term distribution7.2.6 Comparing two sets of raw trades7.3 Conclusions7.4 The Next Step8. Position Sizing8.1 Introduction8.1.1 Fixed position sizing8.1.2 Kelly method8.1.3 Optimal-f8.1.4 Percentage of equity8.1.5 Maximum risk percentage8.1.6 Martingale8.1.7 Anti-martingale8.2 Pyramiding8.3 Conclusions8.4 The Next Step9. Risk9.1 Introduction9.2 Trade Risk9.2.1 Stop-loss orders9.2.2 Using maximum adverse excursion (MAE) to select the stop-loss threshold9.3 Risk of Ruin9.4 Portfolio Risk9.5 Additional Portfolio Metrics9.6 Monte Carlo Analysis9.7 Case Study: Are Stops Useful in Trend Trading System?10. Case Studies10.1 Introduction10.2 A Note about Data10.3 A Note about the Case Studies10.4 Building a Technical Trading System with Neural Networks10.4.1 Splitting data10.4.2 Benchmark initial rules10.4.3 Identify specific problems10.4.4 Identify inputs and outputs for the ANN10.4.5 Train the networks10.4.6 Derive money management and risk settings10.4.7 In-sample benchmarking10.4.8 Out-of-sample benchmarking10.4.9 Decide on final product10.5 Building a fundamental trading system with neural networks10.5.1 Splitting data10.5.2 Benchmark initial rules10.5.3 Identify specific problems10.5.4 Identify inputs and outputs for ANN10.5.5 Train the networks10.5.6 Derive money management and risk settings10.5.7 In-sample benchmarking10.5.8 Out-of-sample benchmarking10.5.9 Decide on final productFinal ThoughtsAppendicesScript SegmentsBibliographyIndex
• Sommario/riassunto: Everybody knows there is potential to make big money in the stock market. But what most people don't know is how to go about it. This book guides you for building rule-based stockmarket trading systems. It shows you how to design, test and trade a rule-based system. It takes a scientific approach in developing trading systems.
• Titolo autorizzato: Designing stock market trading systems
• ISBN: 0-85719-135-7
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910465044703321
• Lo trovi qui: Univ. Federico II