跳到主要內容

臺灣博碩士論文加值系統

(3.236.23.193) 您好!臺灣時間:2021/07/24 12:37
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:蕭立文
研究生(外文):Hsiao, Liwen
論文名稱:主機板高科技司公司市值模擬研究
論文名稱(外文):Simulating the Market Value of Mother Board Technology Corporation
指導教授:游張松游張松引用關係
學位類別:博士
校院名稱:國立臺灣大學
系所名稱:商學研究所
學門:商業及管理學門
學類:一般商業學類
論文種類:學術論文
論文出版年:2000
畢業學年度:88
語文別:中文
論文頁數:145
中文關鍵詞:市值類神經網路模擬事件理論價值主機板
外文關鍵詞:Market ValueNeural NetworkSimulationEventTheoretical ValueMother Borad
相關次數:
  • 被引用被引用:3
  • 點閱點閱:181
  • 評分評分:
  • 下載下載:37
  • 收藏至我的研究室書目清單書目收藏:0
本研究以提出主機板公司市值成長率的理論模型為出發,假設公司理論價值、事件變數和市值成長率之間的存在著函數關係,並透過類神經網路模式,來模擬主機板公司的市值成長率或成長等級。從實驗結果中,驗證了以DCF 指標與25種事件變數,透過某種型態的函數,可以描述主機板公司市值成長率或等級的80%。
模擬方法的發展過程,首先收集25種事件變數與DCF指標,並將事件變數以「方向變碼」和「強度編碼」兩種方式進行整理。接著以類神經網路以及相同的樣本,同時進行兩種不同導向的模擬:第一種是成長率數值的模擬﹔第二種是成長率等級的模擬。比較兩種策略的模擬結果,發現強度編碼的數值模擬能力比方向編碼提昇很多,同時等級模擬的正負號正確率高達92%,而三等級的正確率也高達89%。
為了深入了解模擬模型的特性,研究中更進一步分析了模擬錯誤的樣本狀況,發現可以藉由適當的投資決策邏輯,來迴避模擬模型的缺點。因此,我們也針對模擬模型的應用,整理出低風險導向的投資決策邏輯,來搭配模擬結果的應用。以模擬結果搭配決策邏輯,可以高度掌握獲利機會,並可迴避大部分的風險。
最後,回顧模擬模型發展的過程與體驗,去除不必要的動作,將之整理成步驟化的程序。其中步驟包括:輸入變數的收集整理、樣本期間的考量、編碼方式的要點、類神經網路結構設計、以及變數維度確認、網路適用性實驗,以及模式預測能力的檢驗。這個程序將可供本研究推廣至其他科技業時之參考。
This research examines a new theoretical model for market value growth of motherboard technology companies. The model assumed that market value growth is function of theoretical value and events happened in market. By a series of experiments and simulations with Artificial Neural Network (ANN), the research verify DCF indicator and 25 categories of events variables, which can describe more than 80% variation of market value growth for motherboard companies.
When constructing the ANN simulation model, 25 categories of event variables and DCF indicator were collected. The events were coded with both “affect direction” and “relative strength” concurrently. Than ANN simulations were implemented and compared in two strategies, numerical simulation and growth level classification-oriented. As a result, “relative strength” is out performed than “affect direction”. At the same time, the simulation accuracy of 2 levels and 3 levels classification are up to 92% and 89%.
To investigate the characteristics and avoid the weakness of simulation model, an analysis about error samples is introduced to figure out the proper decision-support logics for investment. After test, it’s approved that the decision support logics can help investors gather profitable investment opportunities with very low risk.
At the end of the dissertation, the researcher summarize the simulation model construction methodology in a step by step procedure, including variables collection and coding, sampling period definition, ANN structure design, input variables verification and convergence test for neural model. This procedure is the key reference for implementing this research on other industries.
封面
目錄
第一章 緒論
第一節 主機板業市值變化的模型探討
一、市值模型探討
二、主機板業市值變因資訊的發生時間
三、主機板業的生態與模擬期間的決定
四、模擬模型的要求
第二節 模型假設、問題定義與研究目的
一、模型假設與問題定義
二、研究目的
第三節 本論文之章節介紹
第二章 文獻探討
第一節 財務預測模型的趨勢與類神經網路的應用
一、人工智慧財務預測模型的特色
二、類神經網路在財務預測領域的研究
三、類神經網路在證券市場預測之研究
第二節 類神經網路的原理介紹
一、倒傳遞類神經網路的基本原理
二、類神經的輸入變數與樣本安排
三、輸出變數規劃與模擬目標
第三節 類神經搭配的變數篩選方法
一、變數刪減與資訊流失的權衡
二、因素分析法之介紹
三、主成份分析之介紹
第四節 事件變數
一、事件相關的研究
二、本研究對事件的觀點
第五節 本章結論
第三章 研究架構與研究方法
第一節 研究架構總覽
一、問題範圍與結構分析
二、研究架構
三、研究流程
第二節 變數整理&樣本規劃
一、變數類別之收集整理
二、事件的收集方式
三、事件變數的編碼方式設計
四、DCF理論價值指標的規劃
五、DCF Indicator的組內標準化
六、樣本規劃
七、樣本組合說明
八、效果指標定義
第三節 類神經網路結構設計
一、隱藏層個數之找尋方式
二、隱藏層最少適用個數實驗規劃
第四節 前導研究規劃
一、理論價值的組內標準化效果實驗規劃
二、DCF與事件分離模擬實驗規劃
三、單一公司市值模擬實驗規劃
第五節 實證研究(一):模擬模型的適用性實驗規劃
一、輸入變數維度實驗規劃
二、模擬模型的收歛性實驗規劃
第六節 實證研究(二):三種模擬策略之預測力實驗規劃
一、樣本組合代表的模擬策略
二、樣本 A 的預測力實驗規劃
三、樣本 B 的預測力實驗規劃
四、樣本 C 的預測力實驗規劃
五、三種策略的比較重點
第七節 本章結論
第四章 樣本處理&前導研究
第一節 變數整理與樣本整理
一、專家意見之整理與變數的確定
二、樣本資料的收集整理
三、事件變數的編碼
四、市值成長率與DCF Indicator的處理
五、本研究採用的四組樣本整理
第二節 類神經網路結構的決定
一、類神經運算結構的決定
二、隱藏層個數的實驗過程&結果
三、分析與討論
四、實驗結論
第三節 DCF組內標準化實驗
一、實驗過程
二、實驗結果分析
三、實驗結論
第四節 單一公司之市值模擬實驗
一、模擬方案描述
二、實驗過程
三、實驗結果分析
四、實驗結論
第五節 DCF與事件分離模擬實驗
一、實驗過程
二、實驗結果分析
三、實驗結論
第六節 本章結論
第五章 實證研究(一):模擬模型的適用性確認
第一節 輸入變數維度實驗
一、以主成份分析進行變數維度實驗
二、以強度編碼反應異常率進行變數維度實驗
三、實驗探討與結論
第二節 收斂性實驗
一、A1樣本的收斂清況
二、B1樣本的收斂清況
三、D1樣本的收斂清況
四、結果分析
五、實驗結論
第三節 本章結論
第六章 實證研究(二):三種模擬策略的預測力評估
第一節 樣本A1的預測力實驗
一、實驗報告
二、實驗結果&分析
第二節 樣本B1的預測力實驗
一、實驗報告
二、實驗結果&分析
第三節 樣本D1的預測力實驗
一、實驗報告
二、實驗結果&分析
第四節 三種策略之預測能力分析
一、數據模擬能力與強度編碼效果
二、分級能力與市值成長率二元編碼的效果
三、不易模擬的樣本狀況分析
第五節 搭配模擬結果之投資決策邏輯
一、以決策邏輯來迴避問題樣本狀況之風險
二、分析結果
三、推論:動態決策邏輯
第六節 本章結論
第七章 研究結果與研究推論
第一節 模擬表現水準評估與模擬策略應用建議
一、三種策略之分級能力表現
二、數值模擬能力的表現
三、模擬方法的結論與建議
第二節 主機板業市值模型的相關推論
一、理論模型對市值成長率的描述能力
二、未驗證部分的原因討論
三、理論模型的結論與建議
第三節 模擬模型之應用推論
一、動態決策邏輯的彈性
二、應用本模擬方法的結論與建議
第四節 以類神經模擬市值變化之方法整理
一、模擬科技公司市值之程序
二、模擬模式建構程序之說明
第五節 研究總結
第六節 本研究應用上的限制
第七節 後續的研究方向
參考文獻
附件 A:華碩公司主力主機板產品推出時間
附件 B:主機板公司前後DCF指標相關性檢定
附件 C:主機板公司之事件記錄表
附件 D:樣本組合
附件 E:短線股價反應與方向不符的事件列表
附件 F:樣本 B1 之主成分分析計算過程
Abecasis, Sara M. and Lapenta, Evangelina S., (1997) “Modelling the MERVAL Index with Neural Networks and the Discrete Wavelet Transform”, Computational Intelligence in Finance, September/October 1997Vol.5, No.5, Page 15~19
Ahmadi, H., (1990) “Testability of the Arbitrage Pricing Theory by Neural Networks”, IEEE International Conference on Neural Network, San Diego, CA., 1990, Pagr I385-I393
Azoff, E. Michael, (1995) “A Method for Extracting Meaning from a Neural Network”, Computational Intelligence in Finance, January/February 1995Vol.3, No.1, Page 7~10
Baestaens, Dirk Emma and Bergh, Willem Max V. D., Eood, Douglas, (1994) “Neural Network Solutions for trading in Financial Markets”, Firs Publishing in Grate British 1994, Pitman Publishing
Baestaens, Dirk Emma and Bergh, Willem Max V. D., (1995) “Tracking the Amsterdam Stock Index Using Neural Networks”, Edited by Apostolos-Paul Refenes, London Business School, England, Neural Network in the Capital Markets, 1995, John Wiley & Sons, Page 149-162
Baker, G. L. and Gollub, J.P., (1998) “Chaotic Dynamics: an Introduction”, second edition 1998, Cambridge University Press
Beltratti, A. Margartia, Sergio and Terna, Pietro, (1996) “Neural Networks for Economic and Financial Modelling”, Fitst Printed 1996, International Thomson Computer Press
Bengio, Y. and Frasconi, P., (1995) "Diffusion of Context and Credit Information in Markovian Models", Neural Network Algorithm, 1995 Vol.3, Pages 249-270.
Bergerson, K. and Wunsch, D.,(1991) “A Commodity Trading Model Based on a Neural Network-Expert System Hybrid”, IEEE International Conference on Neural Network, Seattle, WA., 1991, Page I289-I293
Bodie, Kane and Marcus, (1996) “Investments”, Third Edition 1996, Irwin
Bosarge, W. E.,(1991) “Adaptive Processes to Exploit the Nonlinear Structure of Financial Markets“, Santa Fe Institute of Complexity Conference: Neural Networks and Pattern Recognition in Forecasting Financial Markets, Feb 15, 1991
Bougen, P.D. and Dury, J. C. (1980), “U.K. Statistical Distribution of Financial Ratios”, Journal of Business Finance and Accounting, spr. 1980, Page 39-47
Caldwell, Randall, (1994) “Design of Neural Network-based Financial Forecasting Systems: Data Selection and Data Processing”, Computational Intelligence in Finance, September/October 1994Vol.2, No.5, Page 12~20
Caldwell, Randall B., (1996) “Three Methods of Neural Network Sensitivity Analysis for Input Variable Reduction: A Case Study in Forecasting the S&P 500 Index”, Computational Intelligence in Finance, January/February 1996Vol.4, No.1, Page 16~22
Cho, V., Whrich, B. and Zhang, J., (1999) “Text Processing for Classification”, Computational Intelligence in Finance, March/April 1999Vol.7, No.2, Page 6~22
Chu, Jung, (1996) “Comparing Statistical Method and Artificial Neural Networks in Bankruptcy Prediction”, Unpublished Ph.D Thesis, Warwick Business School, University Of Warwick, 1996
Chung, Hyung-Min Michael and Tam, Kar Yan, (1993) "A Comparative Analysis of Inductive-Learning Algorithms", International Journal of Intelligent Systems in Accounting, Finance and Management, 1993Vol.2-1, Page 3-18.
Coakley, James R. and Brown, Carol E., (1993) "Artificial Neural Networks Applied to Ratio Analysis in the Analytical Review Process.", International Journal of Intelligent Systems in Accounting, Finance and Management, 1993Vol. 2-1, Page 19-39.
Copeland,T., Koller, Tim and Murrin, Jack (1996) “Valuation, Measuring and Managing the Value of Companies”, Second Edition 1996, McKinsey & Company, Inc.
Costantino, M., Collingham, R. J. and Morgan, R. G., (1996) “Qualitative Information in Finance: Natural Language Processing and Information Extraction”, Computational Intelligence in Finance, November/December 1996Vol.4, No.6, Page 14~19
Dohnal, Mirko, (1997) “A Qualitative Approach to Pattern Identification for Financial Data Mining”, Computational Intelligence in Finance, May/June 1997Vol.5, No.3, Page 27~36
Eugene F. Fama and Kenneth R. French, (1996) “The CAPM Is Wanted, Dead or Alive”, Journal of Finance, 1996, December
Eyden, Robert J. V., (1997) “An Appraisal of Various Linear and Nonlinear Methods Utilized for Combining Neural Network Predictors: A Practitioner''''s Perspective”, Computational Intelligence in Finance, September/October 1997Vol.5, No.5, Page 5~14
Fanning, Kurt M. and Cogger, Kenneth O., (1994) "A Comparative Analysis of Artificial Neural Networks Using Financial Distress Prediction", International Journal of Intelligent Systems in Accounting, Finance and Management, 1994 Vol.3-4, Page 241-252.
Johnson, Richard D. and Wichern, Dean W., (1988) “Applied Multivariate Statistical Analysis”, Second Edition 1988, Prentice-Hall, Inc.
Hampton, James, (1999) “Mining Financial News”, Computational Intelligence in Finance, March/April 1999 Vol.7, No.2, Page 53~54
Hatamian, Tim S., (1997) “Predicting Deterministic Chaotic Time Series”, Computational Intelligence in Finance, July/August 1997Vol.5, No.4, Page 14~21
Hoffman, Kenneth and Kunze, Ray,(1971) “Linear Algebra”, Second Edition 1971, Prentice-Hall, Inc.
Horrigan, J. O. (1965) “Some Empirical Bases of Financial Ratio Analysis”, The Accounting Review, July 1965, Page 558-568
Hussain, A., Soraghan, John J. and Durrani, Tariq S., (1997) “A New Neural Network for Nonlinear Time-Series Modeling”, Computational Intelligence in Finance, January/February 1997Vol.5, No.1, Page 16~26
Izumi, Kiyoshi and Ueda, Kazuhiro, (1999) “Analysis of Dealers'''' Processing Financial NewsBased on an Artificial Market Approach”, Computational Intelligence in Finance, March/April 1999 Vol.7, No.2, Page 23~33
Jhee, Won Chul and Lee, Jae Kyu, (1993) "Performance of Neural Networks in Managerial Forecasting.", International Journal of Intelligent Systems in Accounting, Finance and Management, 1993Vol.2-1, Page 55-71.
Kamijo, K. and Tanigawa, T., (1990) “ Stock Price Pattern Recognition: A Recurrent Neural Network Approach“, IEEE International Joint Conference on Neural Network, San Diego, CA., 1990, Pagr I215─I221
Kimoto, T., Asakawa, K., Yoda, M. and Takeoka, M.,(1990) “Stock Market Prediction with Modular Neural Networks“, IEEE International Joint Conference on Neural Network, San Diego, CA., 1990, Pagr I1-I6
Lajbcygier, P., Boek, C., Flitman, A. and Palaniswami, M., (1996) “Comparing Conventional and Artificial Neural Network Models for the Pricing of Options on Futures”, Computational Intelligence in Finance, September/October 1996Vol.4, No.5, Page 16~23
Lajbcygier P., Flitman, A., Swan, A. and Hyndman, R., (1997) “The Pricing and Trading of Options using a Hybrid Neural Network Model with Historical Volatility”, Computational Intelligence in Finance, January/February 1997Vol.5, No.1, Page 27~40
Lanchenbruch, P.A. Sneeringer, C. and Revo, L.T.(1973), “Robustness of the Linear and Quadratic Discriminant Function to Certain Types of Non-Normality,” Communications in Statistics, 1:1, 1973, Page 39-56
Lawrence, Jeannette (1994) “Designing Back Propagation Neural Networks: A Financial Predictor Example”, Computational Intelligence in Finance, January/February 1994Vol.2, No.1, Page 8~13
Malliaris, Mary E., (1995) “A Neural Network Supports the Chaotic Paradigm for the S&P 500 Index”, Computational Intelligence in Finance, May/June 1995Vol.3, No.3, Page 16~21
March, David L., (1995) “Supervised Evolution of the Neural Trader Component of a Stock Portfolio Trading System”, Computational Intelligence in Finance, July/August 1995Vol.3, No.4, Page 7~12
O’Connor, M.C.(1973), “On the usefulness of Financial Ratios to Investors in Common Stock”, The Accounting Review, Apr. 1973, Page 339-352
Opitz, D. and Maclin, R., (1999) "Popular Ensemble Methods: An Empirical Study", Neural Network Algorithm, 1999Vol.11, Pages 169-198.
Pan, Z., Liu, X. and Mejabi, O., (1997) “A Neural-Fuzzy System for Financial Forecasting”, Computational Intelligence in Finance, January/February 1997Vol.5, No.1, Page 7~15
Ross, S. M., “Stochastic Processes,” 開發圖書有限公司,1983
Sen, Tarun K. and Gibbs, Andrew M., (1994) "An Evaluation of the Corporate Takeover Model Using Neural Networks", International Journal of Intelligent Systems in Accounting, Finance and Management, 1994Vol.3-4, Page 279-292.
Sexton, Randall S., (1998) “Identifying Irrelevant Input Variables in Chaotic Time Series Problems: Using a Genetic Algorithm for Training Neural Networks”, Computational Intelligence in Finance, September/October 1998Vol.6, No.5, Page 34~41
Steiner, Manfred and Wittkemper, Hans-Georg, (1995) “Neural Network as an Alternative Stock Market Model”, Edited by Apostolos-Paul Refenes, London Business School, England, Neural Network in the Capital Markets, 1995, John Wiley & Sons, Page 137-148
Taylor, Steven J. & Bogdan, Robert, (1984) “Introduction to Qualitative Research Method”, First Edition 1984, John Wiley & sons
Thomason, Mark R., (1996) “Principal Components Analysis for Neural Network Input Variable Reduction and Financial Forecasting (Part 1)”, Computational Intelligence in Finance, January/February 1996Vol.4, No.1, Page 29~32
Thomason, Mark R., (1997) “A First Multi-Network Hybrid for Financial Forecasting”, Computational Intelligence in Finance, January/February 1997Vol.5, No.1, Page 41~44
Thomason, Mark R. and Caldwell, Randall B., (1998) “Reducing Serial Bias of Direction-Oriented Forecasting Metrics”, Computational Intelligence in Finance, September/October 1998Vol.6, No.5, Page 42~47
White, A. Jay, (1998) “A Genetic Adaptive Neural Network Approach to Pricing Options: A Simulation Analysis”, Computational Intelligence in Finance, March/April 1998Vol.6, No.2, Page 13~23
White, H., (1988) “Economic Prediction Using Neural Networks: The Case of IBM Daily Stock Returns”, IEEE International Conference on Neural Network, July 1988, Page II451-II458
Yoon, Youngohc and Swales, George, (1993) “Predicting Stock Price Performance: A Neural Network Approach“, Computational Intelligence in Finance, September/October 1993 Vol.1, No.1 Page, 14~18
Zapranis, A. D. and Francis, G., (1995) “Modelling Stock Returns in the Framework of APT: A Comparative Study with Regression Models” Edited by Apostolos-Paul Refenes, London Business School, England, Neural Network in the Capital Markets, 1995, John Wiley & Sons, Page101-126
葉怡成,(1999) “應用類神經網路”, 第二版 1999,儒林圖書公司
“資訊工業透析-電腦系統與零組件”, III-0267-J308 1999, 資訊工業策進會MIC
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top