Forecasting exchange rate using Variational Mode Decomposition and entropy theory

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalNot applicablepeer-review

3 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)15-25
Journal / PublicationPhysica A: Statistical Mechanics and its Applications
Volume510
Early online date7 Jun 2018
StatePublished - 15 Nov 2018

Abstract

In this paper, we propose a new exchange rate forecasting model using Variational Mode Decomposition (VMD) with parameter optimization by the combined Mean Square Error (MSE) and Error Entropy (EE) criterion. Exchange rate is decomposed into a series of underlying data components in the transformed multiscale domain using the VMD model. A new MSE–EE criterion is proposed to determine the scale for transient factors among different extracted data components. The proposed model extracts the transient factor more accurately and produces more accurate forecasts. Empirical studies using extensive exchange rates confirmed that the multiscale data structure can be identified more effectively in the decomposed multiscale domain using the proposed methodology. The proposed model demonstrates the superior performance compared to the benchmark models.

Research Area(s)

  • Exchange rate forecasting, Minimum error entropy, Multi-scale analysis, Signal processing, Transient factor, Variational Mode Decomposition