Skip to content

The performance of SVR models highly depends upon the appropriate choice of SVR parameters. Here, different metaheuristic algorithms are used to tune the hyperparameters.

Notifications You must be signed in to change notification settings

ghimohammadr/Metaheuristics_SVR

Repository files navigation

Metaheuristics_SVR

A Matlab implementation of paper "Forecasting stock market with support vector regression and butterfly optimization algorithm" (https://arxiv.org/abs/1905.11462). figBAFlowChart

figBOASVR

Abstract

Support Vector Regression (SVR) has achieved high performance on forecasting future behavior of random systems. However, the performance of SVR models highly depends upon the appropriate choice of SVR parameters. In this study, a novel BOA-SVR model based on Butterfly Optimization Algorithm (BOA) is presented. The performance of the proposed model is compared with many other meta-heuristic algorithms on a number of stocks from NASDAQ. The results indicate that the presented model here is capable to optimize the SVR parameters very well and indeed is one of the best models judged by both prediction performance accuracy and time consumption.

Requirements

MATLAB >= R2019b
LIBSVM -- A Library for Support Vector Machines

Citation

@article{ghanbari2019forecasting,
  title={Forecasting stock market with support vector regression and butterfly optimization algorithm},
  author={Ghanbari, Mohammadreza and Arian, Hamidreza},
  journal={arXiv preprint arXiv:1905.11462},
  year={2019}
}

About

The performance of SVR models highly depends upon the appropriate choice of SVR parameters. Here, different metaheuristic algorithms are used to tune the hyperparameters.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages