| || || Kimata, James Douglas|
| || || Forecasting exchange rate of Solomon Islands dollar using artificial neural network and the purchasing power parity theory|
Author:Kimata, James Douglas
Institution: University of the South Pacific.
Subject: Neural networks (Computer science) -- Solomon Islands, Purchasing power parity -- Solomon Islands -- Mathematical models
Call No.: Pac QA 76 .87 K56 2016
Copyright:Under 10% of this thesis may be copied without the authors written permission
Abstract: With continual changes made and reviews of the exchange rate regime of Solomon Islands it is imperative that a proper forecasting modelling tool is established. The use of neural network models in exchange rate forecasting has received much attention in recent research. In this thesis we propose an artificial neural network (ANN) model for forecasting exchange rates of the Solomon Islands dollar (SBD) against all major trading currencies such as Australian dollar (AUD), Great Britain pound (GBP), Japanese yen (Yen) and EURO. We use daily exchange rate data during the period of January 5, 1998 to June 30, 2014. The proposed model is compared with a naive method as a benchmarked method. Further, it is compared with single exponential smoothing; double exponential smoothing with trend; and Holt-Winter multiplicative and additive seasonal and multiple linear regression models. The performance of the models was measured by using various performance metrics such as root mean square error, mean absolute error, and mean absolute percentage error. The validation tests of the models were also carried out using different goodness of fit measures such as Rsquare, bias and tracking signal. The empirical result reveals that the proposed model is an efficient tool for forecasting SBD against the major trading currencies more accurately than are regression and time series models. We have also tested the purchasing power parity hypothesis using the consumer price index of USA and UK against Solomon Islands for the sample monthly period from January 1993 to December 2013. This thesis uses co-integration and the error correction as methodologies as the data are found to be nonstationary. The result shows that the changes in Solomon dollars (SBD) per USD are influenced by the long-term trends in the price differential of Solomon Islands and the USA. We further investigate the changes in the price differential between Solomon Islands and the UK and establish that they have similar trends. The symmetry and proportionality of the strong version of PPP were found to be very significant for Solomon Islands against UK price only and not against US dollar. The price levels in an open small pegged exchange regime such as that of Solomon Islands are greatly determined by international prices, and interestingly, even the nominal exchange rates are determined by price differentials in the long-run.