Title: A harmony search-based artificial neural network for stock market prediction

Authors: Soumya Das; Sarojananda Mishra; Srinivas Prasad; Manas Ranjan Senapati

Addresses: Department of Computer Science and Information Technology, Government College of Engineering, Kalahandi 766002, Odisha, India ' Department of Computer Science and Engineering, Indira Gandhi Institute of Technology, Saranga 759146, Odisha, India ' Department of Computer Science and Engineering, GMR Institute of Technology, Rajam 523127, Andhra Pradesh, India ' Department of Computer Science and Engineering, Centurion Institute of Technology, Centurion University of Technology and Management, Khurda 752050, Odisha, India

Abstract: For financial time series, the generation of error bars on the point prediction is important in order to estimate the corresponding risk. In recent years, artificial intelligence optimisation techniques have been used to make time series approaches more systematic and improve forecasting performance. The harmony search learning methodology, already successfully applied for training of multilayer perceptrons, is applied to Functional Link Artificial Neural Network (FLANN) in order to infer non-linear models for predicting a time series and the related volatility. The proposed method is implemented and the results are compared with FLANN model trained by back propagation and differential evolution. The proposed training method shows that FLANN-harmony search provides better forecasting/prediction as compared to training the FLANN model using back propagation or differential evolution.

Keywords: FLANN; functional link ANNs; artificial neural networks; harmony search; differential evolution; back propagation; MSE; mean square error; RMSE; root mean square error; stock markets; stock market prediction; financial time series; nonlinear modelling; market volatility; financial forecasting.

DOI: 10.1504/IJBFMI.2015.075323

International Journal of Business Forecasting and Marketing Intelligence, 2015 Vol.2 No.1, pp.19 - 36

Available online: 14 Mar 2016 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article