臺灣博碩士論文加值系統

在股票市場中，投資者根據過去交易資料、市場新聞及財務報告等等公開資料來預測未來股價的趨勢。投資者最關心的就是做正確的預測以為他們帶來利潤，所以，投資者總是致力於提升對股市預測的正確率
從Song與Chissom學者在1993年提出模糊時間序列模型以來，這個模型已被用來預測入學人數、溫度及股價走勢。從文獻探討可知，傳統的方法有個最主要的缺點就是沒有很合理的定義所要觀察的語意值及語意的長度。除此之外，顯而易見的，過去的研究者缺乏股票技術分析理論來支援他們的預測模型，在本論文中，我們以艾略特波浪理論為基礎提出一個時間序列預測模型。因為過去的研究者經常會忽略價與量的關係，更進一步的，我們在提出的預測模型中考慮到價與量之間的關係，我們研究量的技術指標，最終選擇了VR值來對預測值做調整。
為了解決上述的這些問題，我們提出一個適當的方法。傳統的預測模式只根據單一價格指標來預測股價，而沒有考慮其他因素(如：量的指標)，也因為考慮的不夠周到以致於無法正確的預測股價。在本篇論文中，我們提出一個結合波浪理論與模糊雙時間序列的股票指數預測模式來改善預測的正確率，也應用參數α,β及γ來逐漸調整我們的預測模式。我們採用台灣股市加權指數(TAIEX)及美國高科技股票指數(NASDAQ)為預測資料集並與其他方法做比較，實驗結果證明，本研究所提出的模式在預測準確度上優於其它模式。

In stock markets, investors forecast the future price trend based on open data such as past trading data, market news and financial reports. What they care about most is to make accurate predictions to bring profit for them. Therefore, they are absorbed in lifting forecasting accuracy for stock markets.
Fuzzy time-series models have been utilized to forecast the number of enrollment, the height of temperature and stock price patterns since they are first induced by Song and Chissom in 1993. However, from literature, there are two major drawbacks of traditional methods such as the lack of consideration in determining reasonable universe of discourse and the length of intervals. Besides, it is clear to see that the past researchers lacked stock technical analysis theories for supporting their models. Hence, we provide the Elliot’s Wave Principle as the theory base for our forecast model. Furthermore, we consider the relation between price and volume in the proposed model to forecast stock price because it is usually ignored in past researchers. Therefore, we survey the technical indicators of volume and choose the volume ratio, VR, to modify the forecasting values.
In order to solve these problems above, an objective and reasonable approach is then proposed. Traditional forecasting models forecast stock price based on singular price indicator, lacking other factors such as volume indicators, so it is not thoughtful enough to forecast stock price. We propose a wave principle based fuzzy bi-time series model to improve the forecast accuracy, and apply three parameters, alpha, beta and gamma, to refine our forecast model. And set some criteria in order to make trading possible. Using the TAIEX (Taiwan stock index) and NASDAQ (a worldwide famous high-tech industries integrated index in America) as the forecasting datasets, the empirical results show that the proposed model outperforms other conventional models.

摘要 III
Abstract IV
致謝 VI
Content VII
List of Figure IX
List of Table X
1. Introduction 1
1.1 Background and Motivation 1
1.2 Research Objectives 3
1.3 Research Limitations 3
1.4 Organization of This Thesis 4
2. Related works 5
2.1 Fuzzy Time-series Model 5
2.2 Wave Principle and Fibonacci Sequence 8
2.3 The causality relation between price and volume 10
3. Wave Principle based Fuzzy Bi-Time-series Model 13
3.1 Proposed Model 13
3.2 The proposed algorithm 17
4. Verifications and Comparisons 23
4.1 Forecasting for TAIEX 23
4.2 Forecasting for NASDAQ 28
5. Conclusions and Future Research 32
References 34

[1]S.M. Chen: Forecasting enrollments based on fuzzy time-series. Fuzzy Sets and Systems, 81, (1996) 311-319.
[2]S.M. Chen: Temperature Prediction Using Fuzzy Time Series. IEEE Trans. CYBERNETICS, 30(2), (2000) 263-275
[3]S.M. Chen: Forecasting Enrollments Based on High-Order Fuzzy Time Series. Cybernetics and Systems: An Int’l J., 33, (2002) 1-16.
[4]S.M. Chen and C.C. Hsu: A New Method to Forecast Enrollments Using Fuzzy Time Series, Int’l J. Applied Science and Eng., 2(3), (2004) 234-244.
[5]S.H. Chen, C.C. Liao: Agent-based computational modeling of the stock price-volume relation. Information Sciences, 170, (2005) 75-100.
[6]C.H. Cheng etc al.: Trend-Weighted Fuzzy Time-series Model for TAIEX Forecasting, LNCS(SCI), 4234, (2006) 469-477
[7]A.J. Frost, R.R. Prechter, Jr.: Elliott Wave Principle, New Classic Library. (1978)
[8]C.W.J. Granger.: Investigating causal relations by econometric models and cross-spectral methods. Econometrica, 37, (1969) 424-438
[9]J. Giarratano and G.D. Riley: Expert System:Principles and Programming, third ed. Boston: PWS, (1998) 57-91
[10]A. Hodgson, A. Mansur M. Masih, R. Masih: Futures trading volume as a determinant of prices in different momentum phases. International Review of Financial Analysis, 15, (2006) 68– 85.
[11]K. Huarng: Effective lengths of intervals to improve forecasting in fuzzy time series. Fuzzy Sets and Systems, 123, (2001) 387-394.
[12]K. Huarng: Heuristic Models of Fuzzy Time Series for Forecasting. Fuzzy Sets and Systems, 123, (2001) 369-386.
[13]K. Huarng, H.K. Yu: A Type 2 fuzzy time series model for stock index forecasting. Physica A, 353, (2005) 445-462
[14]J.R. Hwang, S.M. Chen, and C.H. Lee: Handling Forecasting Problems Using Fuzzy Time Series. Fuzzy Sets and Systems, 100, (1998) 217-228.
[15]M.J. Kim, S.H. Min, I. Han: An evolutionary approach to the combination of multiple classifiers to predict a stock price index. Expert Systems with Applications, 31, (2006) 241–247
[16]R. Kitt and J. Kalda: Scaling analysis of multi-variate intermittent time series. Physica A, 353, (2005) 480-492.
[17]J. E. Kotick: An Introduction to the Elliott Wave Principle. Alchemist Issue 40, (2004) 12-14
[18]C.H.L. Lee, A. Liu, Member and W.S. Chen: Pattern Discovery of Fuzzy Time Series for Financial Prediction. IEEE Trans. Knowledge and Data Engineering, 18(5), (2006) 613-625
[19]L.W. Lee, L.H. Wang, S.M. Chen and Y.H. Leu: Handling Forecasting Problems Based on Two-Factors High-Order Fuzzy Time Series. IEEE Trans. Fuzzy Systems, 14(3), (2006) 468-477
[20]B. Marc, H. Takato: Volume and individual security returns on the Tokyo Stock Exchange. Pacific-Basin Finance Journal, 7, (1999) 351–370
[21]R. Orchard: NRC FuzzyJ Toolkit for the JavaTM Platform, User’s Guide. September, http://www.iit.nrc.ca/IR_public/fuzzy/fuzzyJDocs/index.html (2006)
[22]C.H. Shen, L.R. Wang: Daily serial correlation, trading volume and price limit: evidence from the Taiwan Market. Pacific-Basin Finance Journal (1998) 251-273
[23]Q. Song and B.S. Chissom.: Fuzzy time-series and its models. Fuzzy Sets and Systems, 54, (1993) 269-277.
[24]Q. Song and B.S. Chissom.: Forecasting enrollments with fuzzy time series—part 1. Fuzzy Sets and Systems, 54, (1993) 1–9.
[25]Q. Song and B.S. Chissom.: Forecasting enrollments with fuzzy time series—part 2. Fuzzy Sets and Systems, 62, (1994), 1–8.
[26]R. Swannel: Refining the Elliott Wave principle with wave analysis. EBSCO Publishing, Futures, (2002) 48-50.
[27]C.C. Tsai, S.J. Wu: A Study for Second-order Modeling of Fuzzy Time Series. Proc. IEEE International Fuzzy Systems Conference Proceedings, (1999) 719-725.
[28]R.C. Tsau, J.C.O Yang and H.F. Wang.: Fuzzy Relation Analysis in Fuzzy Time-series Model. Computers and Mathematics with Applications, 49, (2005) 539-548
[29]C. Wang, S. Chin: Profitability of return and volume-based investment strategies in China’s stock market. Pacific-Basin Finance Journal, 12, (2004) 541– 564
[30]N. Wiener: The theory of prediction. in: E.F. Beckenbach (Ed.), Modern Mathematics for the Engineers, Series 1, McGraw-Hill, New York, 1956 (Chapter 8).
[31]Zadeh, L.A. Fuzzy sets. Inform. and control 8 (1965) 338-353
[32]Zadeh, L.A.: The concept of a linguistic variable and its application to approximate reasoning I. Information Science, 8, (1975) 199-249
[33]Zadeh, L.A.: The concept of a linguistic variable and its application to approximate reasoning Ⅱ, Information Science, 8, (1975) 301-357
[34]Zadeh L.A.: The concept of a linguistic variable and its application to approximate reasoning Ⅲ. Information Science, 9, (1976) 43-80
[35]http://mathworld.wolfram.com/FibonacciNumber.html
[36]http://www.tse.com.tw/ch/index.php
[37]http://finance.yahoo.com/q/hp?s=%5EIXIC