| 研究生: |
紀如龍 Jih, Ru-Long |
|---|---|
| 論文名稱: |
BPN暨RN神經網路與向量誤差修正模型對國內債券價格之預測績效 Exploring the Relative Abilities of Neural Networks and VECM in Forecasting Taiwan's Bond Price |
| 指導教授: |
林修葳
Lin, Hsiou-Wei 蔡瑞煌 Tsaih, Rru--Huan |
| 學位類別: |
碩士
Master |
| 系所名稱: |
商學院 - 國際經營與貿易學系 Department of International Business |
| 論文出版年: | 1996 |
| 畢業學年度: | 84 |
| 語文別: | 中文 |
| 論文頁數: | 82 |
| 中文關鍵詞: | 公債 、殖利率預測 、神經網路 、RN模型 、BPN模型 、向量誤差修正模型 |
| 外文關鍵詞: | Government bond, Yield to maturity, Neural network, RN, BPN, VECM |
| 相關次數: | 點閱:142 下載:0 |
| 分享至: |
| 查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
本研究計畫探討以RN神經網路模型預測國內債券價格的效度。目前一般用於財務預測的神經網路論著主要為BPN模型,惟BPN模型有其限制,所以本研究計畫將(1)分析比較統計計量模型,BPN神經網路,RN神經網路系統對國內公債價格之預測績效。(2)分析不同時期的預測能力,找出景氣和預測變數的關係,同時將比較各個時期統計計量模型和神經網路模型是否同時有效, 抑或有些有效, 有些無效,以探討各工具是否具有互補性或替代性。並探討預測績效是否受到背後經濟環境的影響。
我們研究對象為國內公債,其每日交易資料取樣時間自民國八十一年開始。影響債券價格的因素可拆解成實質利率,預期通貨膨脹率和風險貼水三層面,本研究總體變數之選取,亦循此三項範疇以求周延。
本研究之研究成果對理論及實務應用將有下列三項預期貢獻:(1)比較不同其常的債券在不同景氣狀況下,各不同預測模型的預測效度差異,探討各時期各工具之預測能力,可提供投資實務界對預測工具之選擇,應用與搭配。(2)對債券報酬率預測研究,分析總體變數,利率風險等變數對債券報酬率的影響,可進一步暸解影響債券價格的相關因素及程度。(3)以往神經網路應用在財務預測領域上, 皆以BPN 神經網路為主,此處引進RN神經網路,比較兩者的表現,可提供學術理論界之驗證。
This research project empirically investigates the accuracy of Reasoning Neural Networks (RN) in forecasting Taiwan's bond prices. We explore (1) the relative predictive abilities of Vector Error Correction Model (VECM), which serve as a representative econometric model, Back Propagation Neural Networks (BPN), which is adopted by most current studies in the application of neural networks in finance, and RN, and (2) th3 potential variations in the three models' predictive power in different phases of economic cycle. Specifically, we aim to study if the three models substitute or complementone another. In addition, we explore the extent to which the relativepredictive abilities of the three models varies with underlying macroecomonic factors. The explanatory variables adopted in this study include all potential drives to (real) risk-free rate, expected inflation rate, and riskspremiums.
In this study, we examine the government bond
terms to maturity,coupon rate, and prices of government bonds during 1992-1995. This project would contribute to both academic and application researchin the following three aspects : (1) Few, if any , prior study explores whether and how various neuralnetworks and/or eco- nomic models perform under different macro-economicvariables. Our empirical results may indicate an appropriate model ( ormodels ) to improve forecasting of bond prices. (2) This study shows how RN, BPN, and VECM models perform in forecastinggovernment bonds yields to maturity. (3) The BPN model prevails in financial forecasting. Nevertheless, BPNis subject to a few short comings and may thus be a sub-optimal model. This study analyzes if RN is more cost-effective in forecasting bond prices than BPN.
第一章序論..........1
第一節研究動機..........1
第二節研究背景..........2
第三節研究對象與架構..........4
第二章文獻回顧..........6
第三章研究方法及進行步驟..........8
第一節變數及樣本資料來源..........8
第二節向量誤差修正模型..........12
(一)單根檢定..........12
(二)共整合檢定14
(三)誤差修正模型..........16
第三節神經網路法..........17
(一)神經網路預測工具的優點..........17
(二)神經網路的基本架構..........17
(三)BPN神經網路..........20
(四)RN神經網路..........22
(五)BPN和RN神經網路設計的優缺點比較..........25
第四章研究過程與結果..........26
第一節向量誤差修正模式..........26
(一)以四年期之813建設公債樣本作分析..........26
(二)以五年期之814建設公債樣本作分析..........30
(三)以十年期之831建設公債樣本作分析..........32
第二節神經網路之預測結..........35
(一)BPN神經網路之預測結果..........35
(二)RN神經網路之預測結果..........38
第三節各預測工具之比較與分析..........40
第五章結論與未來研究方向..........48
(一)結論..........48
(二)未來研究方向..........49
附錄一各模式在不同景氣下之趨勢預測結果..........50
附錄二各模式應用於買賣斷交易之模擬結果..........59
附錄三VECM之各參數估計值與t-test顯著結果(813公債)..........67
附錄四參考文獻..........69
"(一)中文部份
1、梁志氏、汪義育(1995),我國總體數列因果關係之非恆定計量研究完全修正向量自迴歸實證方法。
2、婁天威(1993),我國債券市場結構分析與問題探討,臺灣銀行季刊第四十六志第一期,pp.151-202 。
3、黃國忠(1994),台灣利率期間結構之殖利率曲線計量模型,台灣大學財金所碩士論文。
4、黃振明,債券報酬預測模式預測績效之實證比較,台灣工業技術學院管理技術所碩士論文。
5、張維哲(1992),人工神經網路,全欣資訊圖書去司,10月出版。
6、焦李成(1991),神經網路系統理論,儒林圖書去司,10月出版。
7、葉怡成 (1993),類神經網路模式應用與實作,儒林圖書公司,1月出版。
8、蔡瑞煌(1994),The Softening Learning Procedure for The Networks with Multiple Output Nodes,資管評論,第四期,pp.89-93。
9、蔡瑞煌,(1995),類神經網路概論,三民書局,1月出版。
10、蔣廷方,(1994),類神經網路股價預測系統,企銀季刊,4月,pp .40-49。
11、蘇仁,(1994),可轉換公司債評價模式與類神經網路臺灣地區的實證研究,台灣大學財金所碩士論文。
12、蘇家興,(1993),類神經網路在預測臺灣貨幣市場利率上的應用,交通大學資管所碩士論文。
(二)英文部份
1、Baneljee,A. ; Dolado,J. J. ; Galbraith,J.W. ; Hendry,D. F.,(1993),Cointeration,Error Correction and the Econometric Analysis of Nonstationry Data,Published by Oxford University Press Inc.
2、Bergerson,K. ; Wunsch,D.C.,(1991),A Commodity Trading Model Based on a Neural Networks-Expert System Hybird,Proceedings of the International Joint Conference on Neural Network 1991,pp.289-293.
3、Elton,E. J. ; Gruber,M. J. ; Bl8ke,C. R.,(1995),Fundamental Economic Variables,Expected Returns,and Bond Fund Performance,Journal of Finance,Sep,pp.1229-1256.
4、Engle,R. F. ; Granger,C. W. J.,(1987),Co-intergration and Error Correction : Representation,Estimation and Testing,Econometrica,Vo1.55,pp.251-276.
5,Engle,R. F. ; Yoo,B. S.,(1987),Forecasting and Testing in Cointegrated Systems,Journal of Econometrics,Vo1.35,May,pp.143-159.
6,Gmdnitski,G. ; Osburn,L.,(1993),Forecasting S &P500 and Gold Futures Prices: An Application of Neural Networks,Journal of Futures Markets,Vol. 13,NO.6,pp.631-643.
7,Harvey,A. C.,(1990)The Econometric Analysis of Time Series,Second Edition,Published by Philip Allan.
8,Jeffrey,E. S. ; Venkatachalam,A. R.,(1995),A Neural Network Approach to Forecasting Model Selection,Information & Management,Vo1.29,Dec,pp.297-303.
9,Johansen,S. ; Juselius,K.,(1990),Maximun Likelihood Estimation and Inference on Cointegration-With Applications to the Demand for Money,Oxford Bulletin of Economics & Statistics,Vo1.52,May,pp.169-210.
10,Judge,G. G. ; Hill,R. C. ; Griffiths,W. E. ; Lutkepohl,H. ; Lee,T. C.,(1988)Introduction to The Theoy and Practice of Econometrics,Second Edition,Published by John Wiley & Sons,Inc.
11,Kimoto,T. ; Asakawa,K.,(1990),Stock Market Prediction System with Modular Network,IJCNN-90-Wash,Vol. 1,pp.1-6.
12,Krugman,P. R. ; Obstfeld,M.,(1994)International Economics:Theoy and Policy, Third Edition,Published by R.R. Donnelley & Sons Company.
13,Kryzanowski,L. ; Galler,M. ; Wright,D.W.,(1993),Using Artificial Neural Networks to Pick Stocks,Financial Analysis Journal,Jul-Aug.
14,Lapedes,A. ; Farber,R.,(1987),Nonelinear Signal Processing using Neural Networks:Prediction and System Modeling,Los Alamos National Laboratory Report,LA-UR-87-2662.
15,Lee,T. ; White,H.,(1993),Testing for Neglected Nonlinearity in Time Series 1vfodels,Journal of Econometrics,April,pp.269-290.
16,Michael,G. B. ; Stephen,A. L.,(1992),The Treasury Yield Curve as a Cointegrated System,Journal of Financial and Quantitative Analysis,Vol.27,NO.3,Sep,449-464.
17,Phillips,P. C. B. ; Perron,P.,(1988),Testing for a Unit Root in Time Series Regression,Biometrica,Vo1.75,pp.335-346.
18,Rumelhatt,D. E. ; McClelland,1. L.,(1986),Parallel Distributed Processing,Vol. 1,Published by The Massachusetts Institute of Technology.
19,Schoneburg,E.,(1990),Stock Price Prediction using Neural Networks:A Project Report,Neuralcomputing 2,pp.17-27.
20,Swanson N. ; White H.,(1995),A Model-Selection Approach to Assessing the Information in the Term Structure Using Linear Models and Artificial Neural Networks,Joul11al of Business and Economic Statistics,July,pp.265-275.
21,Tsaih,R.,(1995),The Reasoning Neural Network,Annals of Mathematics and Artificial Intelligence,accepted.
22,Tsaih,R.,(1993),The Softening Learning Procedure,Mathematical and Computer Modelling,Vol.18,No.8,pp.61-64."
(限達賢圖書館四樓資訊教室A單機使用)