作者: Agus Sihabuddin , Sri Hartati
DOI: 10.1063/1.4958508
关键词:
摘要: In this paper, an attempt has been made to forecast two major exchange rates USDAUD (US Dolar versus Australian currency) and USDJPY Japanese Yen using Non-Linear Autoregressive (NAR) with monthly period data from January 1975 April 2014. The is collected Bank of England. ecchange forecasting use 3 layer models input, hidden output layer. number nodes are 2, for respectively. Levernberg-Marquardt (LM) learning algorithm used do training. accuracy result the experiments showed that Dstat parameter (60.56%) a bit higher than industry standard but lower (52.11%). MSE 0.3239 7.518 USDJPY.