Welcome to the InfoSci Platform
Efficient Prediction of Stock Price Using Artificial Neural Network Optimized Using Biogeography-Based Optimization Algorithm

Efficient Prediction of Stock Price Using Artificial Neural Network Optimized Using Biogeography-Based Optimization Algorithm

Hitesh Punjabi, Kumar Chandar S.
Copyright: © 2022 |Volume: 17 |Issue: 7 |Pages: 14
ISSN: 1548-1093|EISSN: 1548-1107|EISBN13: 9781668441381|DOI: 10.4018/IJWLTT.303112
Cite Article Cite Article

MLA

Punjabi, Hitesh, and Kumar Chandar S. "Efficient Prediction of Stock Price Using Artificial Neural Network Optimized Using Biogeography-Based Optimization Algorithm." IJWLTT vol.17, no.7 2022: pp.1-14. http://doi.org/10.4018/IJWLTT.303112

APA

Punjabi, H. & Kumar Chandar S. (2022). Efficient Prediction of Stock Price Using Artificial Neural Network Optimized Using Biogeography-Based Optimization Algorithm. International Journal of Web-Based Learning and Teaching Technologies (IJWLTT), 17(7), 1-14. http://doi.org/10.4018/IJWLTT.303112

Chicago

Punjabi, Hitesh, and Kumar Chandar S. "Efficient Prediction of Stock Price Using Artificial Neural Network Optimized Using Biogeography-Based Optimization Algorithm," International Journal of Web-Based Learning and Teaching Technologies (IJWLTT) 17, no.7: 1-14. http://doi.org/10.4018/IJWLTT.303112

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Stock market price prediction has always draws more attention from researchers and analysts. Prediction of stock price is extremely tough task due to the nature of stock data. Therefore, it is needed to develop an efficient model for predicting stock price. This paper explored the use of Feed Forward Neural Network (FFNN) and bio inspired algorithms to develop two efficient models for prediction. The proposed model is based on the ten indicators derived from historical data. Particle Swarm Optimization (PSO) algorithm which inspired from the behavior of bird flocking and Biogeography Based Optimization (BBO) algorithm driven by the geographical distribution of biological organisms is adopted to optimize the parameters of FFNN. Prediction ability of the proposed models is evaluated by using statistical measures. The experimental results demonstrate that the proposed BBO-FFNN is superior to PSO-FFNN and existing methods taken for comparison in terms of prediction accuracy. It is proved that the proposed BBO-FFNN can effectively enhance stock prediction and reduce the prediction error.