Prediction of forex trend movement using linear regression line, two-stage of multi-layer perceptron and dynamic time warping algorithms

Tiong, Leslie Ching Ow * and Ngo, David Chek Ling * and Lee, Yunli * (2016) Prediction of forex trend movement using linear regression line, two-stage of multi-layer perceptron and dynamic time warping algorithms. Journal of ICT, 15 (2). pp. 117-140. ISSN 1675-414X

[img]
Preview
Text
2016 Prediction of Forex Trend Movement using Linear Regression Line, Two-Stage of Multi-Layer Perceptron and Dynamic Time Warping Algorithms.pdf - Published Version

Download (7MB) | Preview

Abstract

Foreign Exchange Currency prediction has become a challenging task since the late 1970s due to uncertainty movement of exchange rates. However, most researchers in this area were neglecting to analyse trend patterns from historical Forex data as input features. Thus, this motivates us to investigate possibility of repeated trend patterns from historical Forex data. This paper aims to investigate the repeated trend patterns as features from historical Forex data, which proposes new combination techniques - Linear Regression Line, two-stage of Multi-Layer Perceptron and Dynamic Time Warping algorithms in order to improve the performance of prediction significantly, thus achieving greater accuracy.

Item Type: Article
Additional Information: First and 3rd authors are with the the Dept. of Computing and Information Systems, Faculty of Science and Technology, Sunway University; 2nd author is with the Vice-Chancellor Office, Sunway University
Uncontrolled Keywords: foreign exchange currency prediction; forex trend movement; multi-layer perceptron; linear regression line; dynamic time warping
Subjects: Q Science > QD Chemistry
Divisions: Sunway University > School of Science and Technology > Dept. Computing and Information Systems
Sunway University > Vice-Chancellor Office
Depositing User: Ms. Molly Chuah
Date Deposited: 31 Oct 2017 08:02
Last Modified: 31 Oct 2017 08:06
URI: http://eprints.sunway.edu.my/id/eprint/651

Actions (login required)

View Item View Item