Copyright by Harish K Subramanian 2004Evolutionary Algorithms in Optimization of Technical Rules for Automated Stock Trading by Harish K Subramanian Thesis Presented to the Faculty of the Graduate School of The University of Texas at Austin in Partial Fulfillment of the Requirements for the Degree of Master of Science in Engineering The University of Texas at Austin December 2004Evolutionary Algorithms in Optimization of Technical Rules for Automated Stock Trading Approved by Supervising Committee: Peter Stone Benjamin Kuipers Joydeep GhoshDedicated to Jacks of All Tradesv Acknowledgements I would like to express my deep gratitude to Dr. Peter Stone for his guidance, advice, and encouragement. It has been great fun and a privilege to conduct research under his supervision. I am grateful to him for the confidence he had in me. I would also like to thank Dr. Benjamin Kuipers and Dr. Joydeep Ghosh for their support. I would like to thank Subramanian Ramamoorthy for providing support and interesting discussion. I would also like to express my gratitude to family and friends for their encouragement and support.vi Abstract Evolutionary Algorithms in Optimization of Technical Rules for Automated Stock Trading Harish K Subramanian, MSE The University of Texas at Austin, 2004 Supervisors: Peter Stone, Benjamin Kuipers The effectiveness of technical analysis indicators as a means of predicting future price levels and enhancing trading profitability in stock markets is an issue constantly under review. It is an area that has been researched and its profitability examined in foreign exchange trade [1], portfolio management [2] and day trading [3]. Their use has been advocated by many traders [4], [5] and the uses of these charting and analysis techniques are being scrutinized [6], [7]. However, despite their popularity among human traders, a number of popular technical trading rules can be loss-making when applied individually, typically because human technical traders use combinations [8], [9] of a broad range of these technical indicators. Moreover, successful traders tend to adapt to market conditions by varying the weight they give to certain trading rules and dropping some of them as they are deemed to be loss-making. In this thesis, we try to emulate such a strategy by developing trading systems consisting of rules based on combinations of different indicators, and evaluating their profitability in a simulated economy. We propose and empirically examine two schemes, using evolutionary algorithms (genetic algorithm and genetic programming), of optimizing the combination of technical rules. A multiple model approach [10a] is used to control agent behavior and encourage unwinding of share position to ensure a zero final share position (as is essential within the framework that our experiments are run in). Evaluation of the evolutionary compositevii technical trading strategies leads us to believe that there is substantial merit in such evolutionary designs (particularly the weighted majority model), provided the right learning parameters are used. To explore this possibility, we evaluated a fitness function measure limiting only downside volatility, and compared its behavior and benefits with the classical Sharpe ratio, which uses a measure of standard deviation. The improved performance of the new fitness function strengthens our claim that a weighted majority approach could indeed be useful, albeit with a more sophisticated fitness function.viii Table of Contents Acknowledgements……………………………………………………………......v Abstract………….……………………………………………………………......vi List of Tables……………………………………………………………………...x List of Figures…………………………………………………………………….xi Chapter 1. Introduction 1 1.1. Motivation................................................................................................1 1.2. Outline......................................................................................................3 Chapter 2. Background and Related Work 4 2.1. Background..............................................................................................4 2.1.1. Literature Survey………………………………………………..4 2.1.2. Relevant Trading Terminology..………………………………..8 2.1.3. Stock Market Simulators………………………………………10 2.1.4. PLAT Domain…………………………………………………10 2.2. Early Agent Design and the need for a Composite Strategy .................14 2.2.1. Static Order Book Imbalance (SOBI) Strategy…..……………15 2.2.2. Market Maker…… …………………………………………..16 2.2.3. Volume Based Strategy ………………………………………17 2.2.4. Multiple Model Strategy………………………………………18 2.2.5. Other Strategies……….……………………………………….20 2.3. Genetic Algorithms and Genetic Programming.....................................20 2.4. Performance Criteria.....................................................................…….22 2.4.1. Sharpe Ratio…………………………………………………...22 2.4.2. Modified Sortino Ratio…………………………..…..………..23 2.5. The Data……………………………………………………..………...24 Chapter 3. Agent Design 25 3.1 Genetic Algorithm Agent (GAA)………………………...………….....25 3.1.1. Genetic Algorithm Implementation Issues.…………………....31ix 3.1.2. Component Strategies or Indicators……..…………………….36 3.1.3. Training……………………………………….………….…....40 3.2. Genetic
View Full Document
Unlocking...