Title: Share price time series forecasting for effective supply chain information exchange

Authors: N. Ayyanathan; A. Kannammal

Addresses: Department of Computer Applications, K.L.N College of Information Technology, Pottapalayam, Sivaganga District, Tamil Nadu – Pin Code-630 611, India ' Department of Computer Applications, Coimbatore Institute of Technology, Civil Aerodrome Post, Coimbatore – 641 104, Tamil Nadu, India

Abstract: This article presents the performance analysis of share price prediction using neural network and support vector machine models. The purpose of the research work is to evaluate the best model for the time series forecasting and share price performance prediction of a leading green coffee export company in the Indian stock market, which would in turn help the various stakeholders of the Indian green coffee supply chain, in taking their important business decisions to improve the information exchange among different echelons of the supply chain. The share price data collected was trained and validated using multilayer perceptron, general regression neural network and support vector machine models. The findings and comparative analysis reveals the better performance of support vector machine among other methods.

Keywords: share price prediction; time series forecasting; multilayer perceptron; support vector machines; SVM; generalised regression modelling; Tata Coffee; Hurst exponent; share prices; supply chain information; information exchange; supply chain management; SCM; neural networks; India; green coffee supply chains.

DOI: 10.1504/IJLSM.2014.062125

International Journal of Logistics Systems and Management, 2014 Vol.18 No.1, pp.139 - 158

Published online: 21 Jun 2014 *

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