Development of Trading Systems using Genetic Programming with a Case Study

Diploma Thesis , 2007 , 96 Pages , Grade: 1.7

Computer Science - Programming

In this thesis Genetic Progrmming is used to create trading systems for the EUR/USD foreign exchange market using intraday data. In addition to the exchange rates several moving averages are used as inputs.
The developed evolutionary algorithm extends the framework ECJ. The created trading systems are being evaluated by a fitness function that consists of a trading simulation. Genetic operators have been adapted to support "node weights". By using these on the one hand macromutaion is tried to be reduced on the other hand the interpretability of the created trading systems is tried to be improved.
Results of experiments show that created trading systems are apparently successfull in profitably using informations contained within the exchange rates. Profits of the created trading systems are maximized by using the optimal position size. It is shown that if the minimum investment period is met the achieved results are optimal even when taking into account the used risk adjusted performance figure.

Inhaltsverzeichnis

• Introduction
  • Motivation
  • Objective and structure
• Basic principles and state of the art
  • Genetic Programming
    • Program Structure
    • Initialization of the GP Population
    • The Genetic Operators
    • Fitness Function
    • Selection
    • Process of the algorithm
    • Crossover, building blocks and schemata
    • Approaches against macromutation
    • Modularization
    • Further approaches for improvement
  • Artificial Neural Networks
  • Components of neural networks
  • Network topologies
  • Learning methods
  • Trading Systems
    • Tape Reader
    • Market timing
    • Position sizing
    • Comparison of trading systems
    • Fundamental versus technical analysis
    • The Currency Market
    • Approaches for the development of trading systems
• Draft
  • Overview
  • Requirements on the software
  • Conception of software
    • The Evolutionary Algorithm
    • The fitness function
• Implementation
  • Components of the developed software
  • Classes of the exchange rate data server
  • Classes of the Evolutionary Algorithm
  • Overview over the framework ECJ
  • Problems during experiments
• Experiment results
  • Results with node weights
    • Results of the training time period
    • Results of the validation time period
    • Results of the test time period
    • Results as monthly turnovers
    • Created trading rules
  • Results without node weights
    • Results of the training period
    • Results of the validation time periods
    • Results of the test period
    • Results as monthly returns
    • Created trading rules
  • Identification and application of optimal f
• Discussion and evaluation
• Outlook
• Summary
• List of figures
• Bibliography
• Glossary

Zielsetzung und Themenschwerpunkte

This diploma thesis aims to develop a trading system for the currency market using Genetic Programming (GP). The goal is to create a system that can automatically learn and adapt to changing market conditions, ultimately achieving profitable trading results. The thesis explores the application of GP in the context of financial markets, specifically focusing on the currency market.

• Genetic Programming (GP) as a tool for automated trading system development
• Application of GP to the currency market
• Design and implementation of a GP-based trading system
• Evaluation of the system's performance through experiments and analysis of results
• Comparison of different GP approaches and their impact on trading performance

Zusammenfassung der Kapitel

The first chapter introduces the motivation behind using Genetic Programming (GP) for developing trading systems. It highlights the success of natural evolution in finding sophisticated solutions and explores the potential of GP to mimic this process for automated program development. The chapter also discusses the challenges of applying GP to financial markets, particularly the currency market, and the need for a system that can adapt to changing market conditions.

Chapter 2 provides a comprehensive overview of the basic principles and state-of-the-art techniques in Genetic Programming and Artificial Neural Networks. It delves into the program structure, initialization, genetic operators, fitness function, selection process, and other key aspects of GP. The chapter also explores the components, topologies, and learning methods of Artificial Neural Networks, highlighting their relevance to trading system development.

Chapter 3 focuses on the design and implementation of the software framework used for developing the GP-based trading system. It outlines the requirements, conception, and key components of the software, including the Evolutionary Algorithm and the fitness function. The chapter also discusses the challenges encountered during the implementation process.

Chapter 4 presents the experimental results obtained from testing the developed trading system. It analyzes the performance of the system in different time periods, including training, validation, and testing phases. The chapter also examines the trading rules generated by the GP algorithm and evaluates their effectiveness in achieving profitable trading results.

Chapter 5 delves into the discussion and evaluation of the experimental results. It analyzes the strengths and weaknesses of the developed trading system, highlighting its potential and limitations. The chapter also explores future directions for research and development in the field of GP-based trading systems.

Schlüsselwörter

The keywords and focus themes of the text encompass Genetic Programming, trading systems, currency market, automated trading, financial markets, machine learning, evolutionary algorithms, artificial neural networks, and performance evaluation. The thesis explores the application of Genetic Programming for developing trading systems that can automatically learn and adapt to changing market conditions, ultimately achieving profitable trading results.

• College: University of Hamburg
• Grade: 1.7
• Author: Holger Hartmann (Author)
• Publication Year: 2007
• Pages: 96
• Catalog Number: V186454
• ISBN (eBook): 9783869436920
• ISBN (Book): 9783869432038
• Language: English
• Tags: development, trading, systems, genetic, programming, case, study