Title: Trading and forecasting performance of different hybrid ARIMA - neural network models for stock returns

Authors: Manish Kumar; M. Thenmozhi

Addresses: CRISIL Global Research and Analytics, TVH Beliccia Tower-II, Block No: 94, MRC Nagar, Chennai 600028, India ' Department of Management Studies, Indian Institute of Technology Madras, Chennai 600036, India

Abstract: This study examines the performance of different hybrid methodologies that combine ARIMA and artificial neural network (ANN) to forecast stock market returns. Two new hybrid ARIMA-ANN models are developed and compared with Zhang's (2003) model on real data sets and the model performance is evaluated using trading performance measures. The study shows that hybrid models outperform independent models and the hybrid ARIMABP model achieves greater accuracy and provides evidence of superiority of the other hybrid models.

Keywords: ARIMA; artificial neural networks; ANNs; hybrid models; stock returns; trading performance; forecasting performance; modelling; stock markets.

DOI: 10.1504/IJMOM.2014.067361

International Journal of Modelling in Operations Management, 2014 Vol.4 No.3/4, pp.137 - 144

Received: 17 Jun 2013
Accepted: 08 Apr 2014
Published online: 14 Feb 2015 *

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