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

Artificial Neural Network and Genetic Algorithm Hybrid Intelligence for Predicting Thai Stock Price Index Trend.

Montri Inthachot1, Veera Boonjing2, Sarun Intakosum1

  • 1Department of Computer Science, Faculty of Science, King Mongkut's Institute of Technology Ladkrabang, Bangkok 10520, Thailand.

Computational Intelligence and Neuroscience
|December 16, 2016
PubMed
Summary

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

A Novel Elderly Tracking System Using Machine Learning to Classify Signals from Mobile and Wearable Sensors.

International journal of environmental research and public health·2021
Same author

Learning recommendation with formal concept analysis for intelligent tutoring system.

Heliyon·2020
See all related articles

This study combined Artificial Neural Networks (ANN) and Genetic Algorithms (GA) for improved stock market prediction. The hybrid model accurately forecasts Thailand

Area of Science:

  • Computational Finance
  • Machine Learning Applications
  • Time Series Analysis

Background:

  • Accurate stock market trend prediction is crucial for financial decision-making.
  • Traditional methods often struggle with the complexity and volatility of financial markets.
  • Feature selection is vital for enhancing the performance of predictive models.

Purpose of the Study:

  • To develop and evaluate a hybrid Artificial Neural Network (ANN) and Genetic Algorithm (GA) model for predicting Thailand's SET50 index trend.
  • To assess the efficacy of GA in optimizing input variable selection for ANN-based financial forecasting.
  • To compare the predictive accuracy of the hybrid model against traditional single-input variable methods.

Main Methods:

  • Utilized Artificial Neural Networks (ANN), a machine learning technique for trend prediction based on historical data.

Related Experiment Videos

  • Employed Genetic Algorithms (GA) for efficient feature selection, identifying optimal subsets of input variables for the ANN.
  • Integrated technical indicators with varying past time spans (3-, 5-, 10-, 15-day) as input variables.
  • Trained and evaluated the hybrid model using 6 years of SET50 index data (2009-2014).

    • Main Results:

    • The hybrid ANN-GA model demonstrated superior accuracy in predicting the SET50 index trend compared to models using single input variables.
    • GA effectively reduced the dimensionality of input variables, selecting the most influential technical indicators for prediction.
    • The model successfully handled a large set of diverse input variables, optimizing predictive performance.

    Conclusions:

    • The integration of Genetic Algorithms with Artificial Neural Networks offers a powerful approach for enhancing stock market trend prediction accuracy.
    • Optimized feature selection through GA is critical for improving the performance of ANN models in financial forecasting.
    • This hybrid intelligence approach provides a more robust and accurate method for predicting the SET50 index trend.