Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Computational learning techniques for intraday FX trading using popular technical indicators.

M H Dempster1, T W Payne, Y Romahi

  • 1Centre for Financial Research, Judge institute of Management, University of Cambridge, Cambridge, UK.

IEEE Transactions on Neural Networks
|February 6, 2008
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Pulmonary lymphoproliferative disorders.

Mayo Clinic proceedings·1993
Same author

Pediatric tracheobronchial foreign bodies. A case report.

Minnesota medicine·1993
Same author

Pulmonary blastomycosis: findings on chest radiographs in 63 patients.

AJR. American journal of roentgenology·1990
Same author

The 60Co gamma-radiolysis of aqueous papain solutions: repair and protection by cysteine.

Radiation research·1971
Same author

Mediastinal and subcutaneous emphysema complicating bronchial asthma in a nine-year-old male.

The Journal of allergy·1961
Same author

THE INFLUENCE OF MINUTE DOSES OF IODINE AND IRON ON GROWTH OF RATS FURNISHED VITAMIN A FREE DIET.

Science (New York, N.Y.)·1928
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

Computational learning strategies for profitable trading rules show promise. Genetic algorithms outperform other methods, especially with transaction costs, but realistic costs limit profitability and overfitting is a risk.

Area of Science:

  • Computational finance
  • Machine learning in finance
  • Algorithmic trading

Background:

  • Technical indicators are widely used in financial markets.
  • Developing profitable trading rules from these indicators is a complex challenge.
  • Computational learning offers potential solutions for automated trading strategy development.

Purpose of the Study:

  • To compare the effectiveness of different computational learning approaches for generating profitable trading rules.
  • To evaluate the performance of reinforcement learning and genetic programming against simpler methods.
  • To analyze the impact of transaction costs and overfitting on trading strategy profitability.

Main Methods:

  • Utilized reinforcement learning and genetic programming as primary computational learning methods.

Related Experiment Videos

  • Compared these with a Markov decision problem exact solution and a heuristic approach.
  • Employed a collection of popular technical indicators as input features for trading rules.

    • Main Results:

    • All methods generated significant profits with zero transaction costs.
    • Genetic algorithms demonstrated superiority in the presence of non-zero transaction costs.
    • No method yielded significant profits at realistic transaction cost levels.
    • A substantial risk of overfitting was identified when in-sample learning was unconstrained.

    Conclusions:

    • Genetic programming is a promising approach for developing trading rules from technical indicators, particularly when accounting for transaction costs.
    • Realistic transaction costs significantly diminish the profitability of automated trading strategies.
    • Careful constraint of in-sample learning is crucial to mitigate overfitting and ensure robust out-of-sample performance.