A multivariate neuro-fuzzy system for foreign currency risk management decision making

Authors:
Vincent C. S. Lee;Hsiao Tshung Wong
Affiliations:
School of Business Systems, Monash University, Melbourne, Building 63, Wellington Road, Clayton, Vic. 3800, Australia;School of Business Systems, Monash University, Melbourne, Building 63, Wellington Road, Clayton, Vic. 3800, Australia
Venue:
Neurocomputing
Year:
2007

Citing 2
Cited 0

Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)
Statistical inference, the bootstrap, and neural-network modeling with application to foreign exchange rates

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.01

Visualization

Abstract

Currency risk management decision involves deciding on when, how much and what hedging instrument (i.e., currency futures or options) should be used to hedge its risk exposure with the base currency. Intuitively the accuracy in forecasting the direction and magnitude of future exchange rate movements is central to currency risk management decision-making process. This research investigates the predictive performance of a hybrid multivariate model, using multiple macroeconomic and microstructure of foreign exchange market variables. Conceptually, the proposed system combines and exploits the merit of adaptive learning artificial neural network (ANN) and intuitive reasoning (fuzzy-logic inference) tools. An ANN is employed to forecast a foreign exchange rate movement which is followed by the intuitive reasoning of multi-period foreign currency returns using multi-value fuzzy logic for foreign currency risk management decision-making. Empirical tests with statistical and machine learning criteria reveal plausible performance of its predictive capability.