ارسل ملاحظاتك

ارسل ملاحظاتك لنا







Forecasting Foreign Exchange Rates An Empirical Study Using the Back Propagation Network to Predict the Japanese Yen Exchange Rates Versus Us Dollar

المصدر: المجلة المصرية للدراسات التجارية
الناشر: جامعة المنصورة - كلية التجارة
المؤلف الرئيسي: Habib, Nagy M. (Author)
مؤلفين آخرين: El Obeid, Magdi (Co-Author), Yousif, Yasir (Co-Author), El Obeid, Muna (Co-Author)
المجلد/العدد: مج32, ع2
محكمة: نعم
الدولة: مصر
التاريخ الميلادي: 2008
الصفحات: 47 - 58
رقم MD: 659905
نوع المحتوى: بحوث ومقالات
قواعد المعلومات: EcoLink
مواضيع:
رابط المحتوى:
صورة الغلاف QR قانون

عدد مرات التحميل

8

حفظ في:
المستخلص: Forecasting exchange rates is actually a very difficult task; because of the many correlated factors that are involved. These factors could be economical, political or psychological. The Backpropagation Network Is a systematic method for training multiplayer artificial Neural Networks. Backpropagation has dramatically expanded the range of problems to which Neural Networks can be applied. It is widely used in natural language processing, image data compression signal processing, character recognition, system modeling, financial and commercial modeling and servo control. The study is designed to forecast currency exchange rates for the Japanese Yen versus US Dollar using the Backpropagation Network. It is divided into three sections. First section is an introduction with a brief description of the Japanese financial sector and review of the literature related to foreign exchange rates determination. The second deals with the Artificial Neural Networks and how they differ from traditional computing and expert systems. The last section provides an analysis of the date and the prediction of the Japanese exchange rates for the period 1996 - 2002. The data used are monthly data for the same period. The conclusion was that a Backpropagation Neural Network is capable of forecasting exchange rates with a high degree of accuracy.