International Journal of Engineering and Technology

Fuzzy time series model has been employed by many researchers in forecasting activities such as students’ enrolment, temperature fluctuations and stock prices. The existing fuzzy time series models require exact match of the fuzzy logic relationships to calculate the forecasted value. However, in real life applications, the exact match of fuzzy logic relationships is not possible. Thus, an improved fuzzy time series model termed as distance-based fuzzy time series model was proposed to remedy this shortcoming and successfully tested to the case of exchange rate data of New Taiwan Dollar (NTD) against United States Dollar (USD). The model was reportedly outperformed the artificial neural network and random walk models for the NTD against USD exchange rate. However, the performance of exchange rate using the distance-based fuzzy times series model for other currencies is still not fully explored. This paper forecasts the exchange rate of Malaysian Ringgit (MYR) against USD and tests the performance of the exchange rate using a distance-based fuzzy time series model. Data of the exchange rate USD against MYR from 11 August 2009 to 15 September 2009 were tested to the forecasting model. A sample of performance comparison between data sets of MYR against USD and NTD against USD was conducted. Under the same forecasting model, it is found that the forecasting errors for MYR against USD were smaller than NTD against USD exchange rate. The experiment results show that the forecasted exchange rate of MYR against USD has performed better under the distance-based fuzzy time series model.