Title: Forecasting foreign exchange rates using CRO based different variants of FLANN and performance analysis

Authors: Kishore Kumar Sahu; Soumya Ranjan Sahu; Sarat Chandra Nayak; Himansu Sekhar Behera

Addresses: Department of Computer Science and Engineering and Information Technology, Veer Surendra Sai University of Technology (VSSUT), Burla, Sambalpur-768018, Odisha, India ' Department of Computer Science and Engineering and Information Technology, Veer Surendra Sai University of Technology (VSSUT), Burla, Sambalpur-768018, Odisha, India ' Department of Computer Science and Engineering and Information Technology, Veer Surendra Sai University of Technology (VSSUT), Burla, Sambalpur-768018, Odisha, India ' Department of Computer Science and Engineering and Information Technology, Veer Surendra Sai University of Technology (VSSUT), Burla, Sambalpur-768018, Odisha, India

Abstract: Globalisation has been the most influential shift of human civilisation since its inception. Foreign exchange (FOREX) market rates played a pivotal role in this extravagant change. FOREX rates have been a vital factor while deciding any international deals among the countries. Though FOREX exhibits a nonlinear trend, evolutionary techniques like artificial neural networks (ANNs) make it possible to predict. This paper deliberates the prediction using different variants of FLANN, i.e., CFLANN, LFLANN, PFLANN and TFLANN with chemical reaction optimisation (CRO) technique by using the real-time series of rupees, euro, yen and pound. Experimental analysis indicates that PFLANN and LFLANN perform better in most of the cases.

Keywords: functional link ANNs; artificial neural networks; FLANN; foreign exchange rates; FOREX; exchange rate forecasting; chemical reaction optimisation; CRO; rupees; yen; dollars; pounds; performance evaluation.

DOI: 10.1504/IJCSYSE.2016.081380

International Journal of Computational Systems Engineering, 2016 Vol.2 No.4, pp.190 - 208

Received: 28 Jul 2015
Accepted: 20 Jun 2016
Published online: 06 Jan 2017 *

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