The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON SYSTEMS
Transactions ID Number: 29-675
Full Name: Kuentai Chen
Position: Assistant Professor
Age: ON
Sex: Male
Address: 84 Gungjuan Road, Taishan, Taipei Hsien 243,
Country: TAIWAN
Tel: +886 2 0910102881
Tel prefix: 0910102881
Fax:
E-mail address: kuentai@mail.mcut.edu.tw
Other E-mails: kch5207@hotmail.com
Title of the Paper: The Prediction of Taiwan 10-Year Government Bond Yield
Authors as they appear in the Paper: KUENTAI CHEN1, HONG ¡VYU LIN2*, TZ¡VCHEN HUANG
Email addresses of all the authors: kuentai@mail.mcut.edu.tw, hylin@mail.mcut.edu.tw
Number of paper pages: 10
Abstract: Neural Networks are nowadays a promising technique in various financial applications. Numerous studies have demonstrated that the Neural Networks are accurate and efficient. Yet research for the field of forecasting government bond yield is short. Among these limited number of studies, Backpropagation network (BPN) seems to be the most used method. However, suffering form the potential problems, such as slow training speed, long processing time, and possible local minimum, BPN may not be the best solution for all applications in practice. The purpose of this research is to provide an in-depth study of effects of on the performance of different neural networks in Taiwan¡¦s 10-year government bond yields forecasting. Five selected models with different structures, namely Backpropagation network (BPN), Resilient Propagation (RPROP), Radial Basis Function Neural Network (RBFN), Adaptive Neuro-Fuzzy Inference Systems (ANFIS), and Support Vector Regression (SVR), are inv!
estigated and the results are analyzed and compared. The results indicate that (1) the number of nodes in the hidden layer is insensitive to the prediction. (2) The recommended number of input nodes is five. (3) More training samples do enhance forecasting performance in our study. (4) The performance of RBFN is the best, followed by ANFIS and RPROP, SVR, and then BPN. (5) BPN is efficient but not the best approach. (6) Our result reveals that RBFN is a useful predicting approach in government bond yield, it performs better than other four models. The recommended structure for RBFN in this application is five input nodes, six center nodes in the hidden layer, and one output node.
Keywords: government bond, yield, forecasting, artificial neural network, neural networks, Radial Basis Function
EXTENSION of the file: .pdf
Special (Invited) Session: The Prediction of Taiwan Government Bond Yield by Neural Networks
Organizer of the Session: 620-511
How Did you learn about congress:
IP ADDRESS: 220.133.65.98
