跳到主要內容

臺灣博碩士論文加值系統

(44.213.63.130) 您好!臺灣時間:2023/02/01 00:49
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:黃姿禎
研究生(外文):Tz-Chen Huang
論文名稱:公債殖利率預測-應用各種類神經網路之實證研究
論文名稱(外文):Forecasting Government Bond Yield Using Various Artificial Neural Networks
指導教授:陳琨太陳琨太引用關係
學位類別:碩士
校院名稱:明志科技大學
系所名稱:工程管理研究所
學門:工程學門
學類:綜合工程學類
論文種類:學術論文
論文出版年:2006
畢業學年度:94
語文別:中文
論文頁數:50
中文關鍵詞:公債殖利率預測類神經網路
外文關鍵詞:government bondyieldforecastingartificial neural network
相關次數:
  • 被引用被引用:3
  • 點閱點閱:524
  • 評分評分:
  • 下載下載:264
  • 收藏至我的研究室書目清單書目收藏:3
雖然許多文獻已經證實類神經網路對於財管領域的預測績效良好,但是將之應用在債券殖利率預測的相關研究仍然缺乏,再者,這些研究大多也僅採用倒傳遞類神經網路作為預測工具。倒傳遞類神經網路有學習速度慢、執行時間過長、以及容易陷入局部最小值的困擾,而這些問題的存在,恐怕將會影響預測的準確性,所以,本研究嘗試運用彈性倒傳遞演算法、輻狀基底函數類神經網路、調適性網路模糊推論系統、與倒傳遞類神經網路,針對臺灣十年期指標公債殖利率作一預測,希望藉由比較不同類神經網路模型,推估出預測臺灣公債殖利率上相對較佳之預測模型。
我們的研究結果顯示:(1)四種類神經網路的隱藏層參數與平均絕對誤差百分比之間並無一規律可遵循。(2)對本研究所使用之類神經網路模型與臺灣十年期指標公債資料而言,輸入層節點數以四或五個較佳。(3)較長的訓練資料時間確實有助於提升類神經網路模型的預測準確度。(4)整體預測表現上,以輻狀基底函數類神經網路模型預測結果相對最佳,其次為調適性網路模糊推論系統、彈性倒傳遞演算法,使用最陡坡降法的倒傳遞類神經網路則較差。(5)於臺灣十年期指標公債的預測上,我們建議使用輻狀基底函數類神經網路,其模型參數設定為五個輸入層節點,六個隱藏層中心點個數及一個輸出節點。
Numerous studies have shown that artificial neural networks which have good performance can be one of the very useful tools in financial prediction. However, the field is still short of government bond yield forecasting, and even there are a few published papers in this area, these conventional forecasting models only rely on BPN. Unfortunately, BPN have some potential problems which includes slow training speed, long processing time, and possible local minimum. In practice, it may lead to poor forecasting ability and have incorrect result. The purpose of this research is to provide an in-depth study of effects of four selected models on the performance of neural networks in government bond yields forecasting. Specifically, we examine and compare four neural network models(RPROP, RBFN, ANFIS and BPN) on the forecasting performance of government bond yield. The results indicate that (1)MAPE is shown to be insensitive to the number of hidden layer. (2)The suitable number of input nodes are four or five. (3)Obviously, large training samples do enhance forecasting performance in our study. (4)The predictable performance of RBFN is the best, followed by ANFIS and RPROP, and then the gradient steepest descent method of BPN. (5)Our result reveals that RBFN is a useful predictable approach in government bond yield better than other three neural network models. Recommended parameters for in RBFN are five input nodes, six internal nodes of hidden layer, and the output layer contained a single node with an acceptable degree of accuracy.
目錄
論文指導教授推薦書 i
論文口試委員審定書 ii
明志科技大學學位論文授權書 iii
博碩士論文電子檔案上網授權書 iv
致謝 v
中文摘要 vi
英文摘要 vii
目錄 viii
圖目錄 x
表目錄 xi
第一章 緒論 1
第一節 研究動機與目的 1
第二節 本文架構 5
第二章 文獻回顧 6
第一節 與股票相關文獻 7
第二節 與期貨相關文獻 9
第三節 與匯率相關文獻 10
第四節 與債券相關文獻 12
第三章 研究方法 17
第一節 類神經網路模型 17
第二節 研究流程 23
第三節 資料來源與應用軟體 25
第四節 網路預測績效之評量標準 25
第四章 實證結果 27
第一節 樣本資料 27
第二節 類神經網路之預測結果 29
第三節 各類神經網路模型之比較與分析 37
第五章 結論與建議 41
參考文獻 43
附錄一 48
附錄二 50
圖目錄
圖2.1 神經元模型 6
圖3.1 倒傳遞類神經網路架構圖 17
圖3.2 輻狀基底函數類神經網路架構圖 20
圖3.3 調適性網路模糊推論系統架構圖 22
圖3.4 研究流程圖 24
圖4.1 臺灣十年期指標公債殖利率走勢圖 27
圖4.2 倒傳遞類神經網路在985筆訓練樣本數之預測模型 31
圖4.3 彈性倒傳遞演算法在985筆訓練樣本數之預測模型 33
圖4.4 輻狀基底函數類神經網路在985筆訓練樣本數之預測模型 35
圖4.5 調適性網路模糊推論系統在985筆訓練樣本數之預測模型 37
表目錄
表4.1 類神經網路設定條件 28
表4.2 倒傳遞類神經網路在不同輸入層節點數之預測結果 29
表4.3 倒傳遞類神經網路在不同隱藏層節點數之預測結果 30
表4.4 彈性倒傳遞演算法在不同輸入層節點數之預測結果 31
表4.5 彈性倒傳遞演算法在不同隱藏層節點數之預測結果 32
表4.6 輻狀基底函數類神經網路在不同輸入層節點數之預測結果 33
表4.7 輻狀基底函數類神經網路在不同隱藏層中心點個數之預測結果 34
表4.8 調適性網路模糊推論系統在不同輸入層節點數之預測結果 36
表4.9 調適性網路模糊推論系統在不同隸屬函數之預測結果 36
表4.10 四種類神經網路在不同訓練筆數之預測結果 38
表4.11 倒傳遞類神經網路在新增樣本數與不同輸入層節點數之預測結果 39
表4.12 臺灣十年期指標公債-類神經網路模型預測結果之比較 39
表4.13 臺灣十年期指標公債-類神經網路模型最佳參數設定組合 40
1.中華民國證券櫃檯買賣中心(2004),中華民國證券櫃檯買賣中心九十三年度年鑑。
2.中華民國證券櫃檯買賣中心(2004),證券櫃檯月刊九十三期。
3.林修葳,蔡瑞煌,紀如龍 (1997),「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」,證券市場發展季刊,第9卷,第1期,頁63-113。
4.紀桂銓 (1993),類神經網路對股市反轉點之學習與應用,交通大學資管所碩士論文。
5.張東揚 (2002),遺傳演化類神經網路在台灣公債殖利率預測之研究,東吳大學經濟學系碩士論文。
6.張斐章、張麗秋、黃浩倫 (2003),類神經網路-理論與實務,台北:台灣東華書局股份有限公司。
7.蘇仁 (1994),可轉換公司債評價模式與類神經網路-台灣地區的實證研究,台灣大學財務金融研究所碩士論文。
8.Bergerson, K. and D. C. Wunsch (1991). “A Commodity Trading Model Based on a Neural Network-Expert System Hybrid.” IJCNN-91, Vol.I, pp.289-293.
9.Chang, F. J. and Y. C. Chen (2003). “Estuary Water-Stage Forecasting by Using Radial Basis Function Neural Network.” Journal of Hydrology, Vol.270, pp.158-165.
10.Cybenco, G. (1989). “Approximation by Superpositions of a Sigmoidal Function.” Mathematics of Control, Signals and Systems, Vol.2, No. 4, pp.303-314.
11.Fama, E. F. (1965). “Mandelbrot and the Stable Paretian Hypothesis.” Journal of Business, Vol.38, pp.34-105.
12.Freeman, J. A. and D. M. Skapura (1992). Neural Networks:Algorithms, Application, and Programming Techniques. Addison-Wesley.
13.George, S. Jr. and Y. Young (1992). “Applying Artificial Neural Networks to Investment Analysis.” Financial Analysts Journal, Vol.48, pp.78-80.
14.Grudnitski, G. and L. Osburn (1993). “Forecasting S&P and Gold Future Prices : An Application of Neural Networks.” The Journal of Futures Markets, Vol.13, No.6, pp.631-643.
15.Hagan, M. T. and M. B. Menhaj (1994). “Training Feedforward Networks with the Marquardt Algorithm.” IEEE Tansactions on Neural Networks, Vol.5, No.6, pp.989-993.
16.Hush, D. R. and B. G. Horne (1993). “Progress in Supervised Neural Networks.” IEEE Signal Processing Magazine, Vol.10, No.1, pp.8-39.
17.Hornik, K., Stinchcombe, M. and H. White (1989). “Multilayer Feedforward Networks are Universal Approximations.” Neural Networks, Vol.2, No.5, pp.359-366.
18.Jang, J. S. R. (1993). “ANFIS: Adaptive Network-based Fuzzy Inference System.” IEEE Transactions on Systems, Man, and Cybernetics, Vol.23, No.3, pp.665-685.
19.Krishnaswamy, C. R., Gilbert, E. W. and M. M. Pashley (2000). “Neural Network Applications in Finance:A Practical Introduction.” Financial Practice and Education, pp.75-84.
20.Kosaka, M., Mizuno, H., T. Sasaki, R. Someya, and N. Hamada (1991). “Applications of Fuzzy logic/Neural Network to Securities Trading Decision Support System.” IEEE, pp.1913-1919.
21.Kimoto, T. and K. Asakawa (1990). “Stock Market Predication System with Modular Networks.” IJCNN-90-Wash, Vol.I, pp.1-6.
22.Kuan, C. and H. White (1994). “Artificial Neural Networks: An Econometric Perspective.” Econometric Reviews, Vol.13, No.1, pp.1-91.
23.Kwok, T. Y. and D. Y. Yeung (1997). “Constructive Algorithm for Structure Learning in Feedforward Neural Networks for Regression Problems.” IEEE Tansactions on Neural Networks, Vol.5, pp.630-645.
24.Lai, C.C., Hsu, Y. and R. Tsaih (1998). “Forecasting S&P 500 stock index futures with a hybrid AI system.” Decision Support Systems, Vol.23, pp.161-174.
25.Lakshmi, S. N. and L. N. Rama (2002). “Stock Market Prediction:A Comparative Study of Multiple Variate Statistical and Artificial Neural Network Models.” Journal of Accounting and Finance Research, Vol.10, No.2, pp.85-94.
26.Lapedes, A. and R. Farber (1987). “Nonlinear Signal Processing Using Neural Networks: Prediction and System Modeling.” Los Alamos National Laboratory Report.
27.Lin, C. T. and C. S. G. Lee (1996). Neural Fuzzy System. New Jersey:Prentice-Hall Inc.
28.Lucas, R. E. (1976). “Econometric Policy Evaluation:A Critique.” Carnegie-Rochester Conference Series on Public Policy, Vol.1, pp.19-46.
29.Mandelbrot, B. (1963). “The Variation of Certain Speculative Prices.” Journal of Business, Vol.36, pp.394-419.
30.Michael, P., Nobay, A. R. and D. A. Peel (1997). “Transactions Costs and Nonlinear Adjustment in Real Exchange Rates: An Empirical Investigation.” Journal of Political Economy, Vol.105, No.4, pp.862-879.
31.Moody, J. and C. Darken (1988). “Learning with Localized Receptive Fields.” Proceedings of the 1988 Connectionist Models Summer School, Carnegie Mellon University, Pittsburgh, PA. San Mateo, CA Morgan Kaufmann Publishers.
32.Makridakis, S. (1993). “Accuracy Measures: Theoretical and Practical Concerns.” International Journal of Forecasting, Vol.9, No.4, pp.527-529.
33.Niyogi, P. and F. Girosi (1996). “On the Relationship between Generalization Error, Hypothesis Complexity, and Sample Complexity for Radial Basis Functions.” Neural Computation, Vol.8, No.4, pp.819-842.
34.Refenes, Apostolos-Paul and A. Zaidi (1995). “Managing Exchange Rate Prediction Strategies with Neural Networks.” In A.P. Refenes, Ed., Neural Networks in the Capital Markets, Chichester, England, John Wiley and Sons, pp.213-219.
35.Rumelhart, D. E., Hinton, G. E. and R. J. Williams (1986). “Learning Representations by Back-Propagating Errors.” Nature, Vol.323, pp.533-536.
36.Riedmiller, M. and H. Braun (1993). “A Direct Adaptive Method for Faster Backpropagation Learning: The RPROP Algorithm.” In Proceedings of the IEEE International Conference on Neural Networks, pp.586-591.
37.Sfetsos, A. and C. Siriopoulos (2004). “Combinatorial Time Series Forecasting Based on Clustering Algorithms and Neural Networks.” Neural Computing and Applications, Vol.13, No.1 pp.56-64.
38.Tsaih, R. (1998). “An Explanation of Reasoning Neural Networks.” Mathematical and Computer Modelling, Vol.28, No.2, pp.37-44.
39.Tsoukalas, L. H. and R. E. Uhrig (1997). Fuzzy and Neural Approaches in Engineering. New York:Wiley and Sons.
40.Vellido, A., Lisboa, P. J. G. and J. Vaughan (1999). “Neural Networks in Business: a Survey of Applications (1992-1998).” Expert Systems with Applications, Vol.17, pp.51-70.
41.Wu, B. (1995). “Model-free Forecasting for Nonlinear Time Series: with Application in Exchange Rates.” Computational Statistics and Date Analysis, Vol.19, No.4, pp.433-459.
42.Zhang, G. and M. Y. Hu (1998). “Neural Network Forecasting of the British Pound/US Dollar Exchange Rate.” Journal of Management Science, Vol.26, No.4, pp.495-506.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top