臺灣博碩士論文加值系統

本研究旨在透過彈性倒傳遞神經網路股價預測與應用在技術指標上的有效性探討，首先，本研究通過特徵變數轉換與變數篩選提高模型學習速度，而針對最佳隱藏層採用逐步測試法尋找，並且設定訓練停止條件，最後選擇彈性倒傳遞演算法建構股價預測模型，訓練好後模型將透過本研究設定的模型評估方法進行評估，最終將模型導入測試組應用於技術指標，搭配策略產生訊號進行有效性評估。
研究結果發現在本研究中，R語言神經網絡套件neuralnet的應用下，本研究模型預測股票價格在中長期趨勢可以得到有效預測，並且股價預測可以應用於技術指標轉換成預測信號，它可以為投資者提供交易操作參考，並根據不同的技術指標策略構建不同的股價預測模型，以提高其預測精度，獲得更有效的投資參考信號。

The purpose of this research is to apply stock technical indicators to the effectiveness of machine learning in predicting stock prices. First of all, this study uses feature variable transformation and variable screening to improve the speed of model learning, and uses a step-by-step test method to find the best hidden layer, and set training stop conditions. Finally, this study chooses Resilient Back-propagation method to build stock price forecasting model, and summarizes the model assessment method established in this study. Finally, the model will use test data to apply to stock technical indicators, and evaluate the effectiveness of the combination of technical indicators strategy and model.
The study finds that in this study, under the application of the R-language neuralnet suite, the model predicts stock prices can be effectively forecasted on mid-to-long-term trends, and the forecast of stock prices can be applied to technical indicators and converted into prediction signals. It can provide investors with transaction operation reference, and based on different technical indicator strategies, different price forecasting models can be constructed to improve its prediction accuracy and obtain more effective investment reference signals.

摘要 I
Abstract　 II
目錄　 III
圖目錄　 IV
表目錄　 V
第壹章　緒論 1
第一節　研究背景 1
第二節 研究動機 2
第三節 研究目的 3
第四節 研究架構 4
第貳章　文獻探討 6
第一節 技術面有效性 6
第二節 股價預測分析 8
第三節 神經模型優化 12
第參章　研究方法 15
第一節 研究資料 15
第二節 模型優化 16
第三節 彈性倒傳遞神經網路 18
第四節 技術指標應用 21
第肆章　研究結果 23
第一節 特徵篩選分析 23
第二節 隱藏層分析 25
第三節 彈性倒傳遞神經網路 29
第四節 技術指標應用 38
第伍章　結論與建議 50
參考文獻 52

李惠妍，「類神經網路與迴歸模式在台股指數期貨預測之研究」，國立成功大學企業管理學系專班
碩士論文，2003年。
李瑞東，「股價報酬率之研究-以台灣股價指數為例」，私立中華大學科技管理研究所碩士論文，
2006年。
葉怡成，「類神經網路模式應用與實作」修訂八版，台北:儒林圖書公司，2003年。
陳國安，「台灣股市電子股報酬率之預測--類神經網路與GARCH模型之應用」，私立東海大學管理
研究所碩士論文，1999年。
陳昌捷，「以倒傳遞類神經網路預測股市指數」，國立宜蘭大學多媒體網路通訊數位學習在職專班
碩士論文，2015年。
翁龍翔，「各國股市技術分析的有效性」，國立臺灣大學財務金融學系碩士論文，1994年。
張修明，「應用倒傳遞類神經網路及時間序列法建構股價報酬率預測模型-以台灣股市為例」，國
立屏東科技大學資訊管理系所碩士論文，2012年。
鄭健毅，「應用SVR支援向量迴歸模式來進行電子產業股價預測」，明新科技大學工業工程與管理
研究所碩士論文，2010年。
劉宛鑫，「運用股價原始資訊建構股價預測模型－類神經網路之應用」，國立高雄第一科技大學金
融營運所碩士論文，2002年。
蔡宜龍，「台灣股票市場技術分析指標有效性之衡量」，國立成功大學工業管理研究所碩士論文，
1990年。
Atsalakis, G.S., & Valavanis, K.P. “Forecasting Stock Market Short-Term Trends
Using a Neuro-fuzzy Based Methodology”, Expert Systems with Applications,
Vol. 36(7), 2009, pp.10967-10707.
Chia-Chi Chen, Chun Kuo, Shu-Yu Kuo, & Yao-Hsin Chou. “Dynamic Normalization
BPN for Stock Price Forecasting”, In International Conference on Systems,
Man, and Cybernetics (SMC), IEEE, 2015, pp.2855-2860.
Chen, A.S., Leung, M.T., & Daouk, H. “Application of Neural Networks to an
Emerging Financial Market: Forecasting and Trading the Taiwan Stock
Index”, Computers & Operations Research, Vol. 30(6), 2003, pp.901-923.
Chong Terence Tai-Leung. & Ng Wing-Kam. “Technical Analysis and The London
Stock Exchange: Testing The MACD and RSI Rules Using The FT30”, Applied
Economics Letters, Vol. 15, 2008, pp.1111-1114.
Dase, R.K. ＆ Pawar, D.D. “Application of Artificial Neural Network for Stock
Market Predictions: A Review of Literature”, International Journal of
Machine Intelligence, ISSN: 0975–2927, Vol. 2(2), 2010, pp.14-17.
Fernando, FR., Christian, GM., & Simon SR. “On The Profitability of Technical
Trading Rules Based on Artificial Neural Networks: Evidence From The
Madrid Stock Market.” Economics Letters, Vol.69 (1), 2000, pp.89–94.
Fifield, S.G.M., Power, D.M., & Knipe, D.G.S. “Moving Average Rules of
Performance in The Emerging Gupiaoshichang”, Journal Form Letter
Economics, Vol. 15(14), 2008, pp.1111-1114
Gocken, Mustafa., Ozcalici, Mehmet., Boru, Asli., Dosdogru, A.T. “Integrating
Metaheuristics And Artificial Neural Networks for Improved Stock Price
Prediction”, Vol.44, 2016, pp.320-331.
Hebb, D.O. “The Organization of Behavior: A Neuropsychological Theory”,
Psychology Pr,2002.
John, McCarthy, ＆ Edward, Feigenbaum. “In Memoriam Arthur Samuel: Pioneer in
Machine Learning", AI Magazine. AAAI, 11(3), 1990.
Kara, Y., Boyacioglu, M.A., & Baykan, Ö.K. “Predicting Direction of Stock
Price Index Movement Using Artificial Neural Networks and Support Vector
Machines: The Sample of The Istanbul Stock Exchange”, Expert Systems with
Applications, Vol. 38(5), 2011, pp.5311–5319.
Kwon,Y.K.,& Moon,B.R. ”Daily Stock Prediction Using Neuro-Genetic Hybrids”,
Genetic and evolutionary computation conferenceon on Genetic and
evolutionary computation:PartII,2003, pp:2203-2214
Lapedes, A., ＆ Farber, R. “Nonlinear Signal Processing Using Neural Networks:
Prediction and System Modelling”, IEEE international conference on neural
networks, San Diego, CA, USA, 1987, Jun 21.
Levy, R.A. “Relative Strength as a Criterion for Investment Selection”,
Journal of Finance, Vol. 22(4), 1967, pp.595-610.
Liu, H., ＆ Wang, J., “Integrating Independent Component Analysis and
Principal Component Analysis with Neural Network to Predict Chinese Stock
Market”, Vol. 2011, 2011, pp.1-15.
Li, X., Chen, F., Sun, D., ＆ Tao, M., “Predicting Menopausal Symptoms with
Artificial Neural Network”, Expert Systems with Applications, Vol. 42(22),
2015, pp.8698-8706.
M. Riedmiller, ＆ H. Braun., “Rprop: A Fast Adaptive Learning Algorithm”.
International Symposium on Computer and Information Science VII. Antalya,
Turkey, 1992, pp.279 - 286.
Patel, Jigar.,Shah, Sahil., Thakkar, Priyank., Kotecha, K., “Predicting Stock
and Stock Price Index Movement Using Trend Deterministic Data Preparation
and Machine Learning Techniques”, Expert Systems with Applications, Vol.
42(1), 2015, pp.259-268.
Patel, Jigar., Shah, Sahil., Thakkar, Priyank., & Kotecha, K., “Predicting
Stock Market Index Using Fusion of Machine Learning Techniques”, Expert
Systems with Applications, Vol. 42(4), 2015, pp.2162-2172.
Qiu, M., & Yu, Song. “Predicting the Direction of Stock Market Index Movement
Using an Optimized Artificial Neural Network Model”, US National Library
of Medicine National Institutes of Health, Vol. 11(5), 2016, PMC4873195.
Qiu, M., & Yu, Song, & Akagi Fumio. “Application of Artificial Neural Network
for The Prediction of Stock Market Returns: The Case of The Japanese Stock
Market”, Chaos, Solitons & Fractals, Vol. 85, 2016, pp.1-7.
Rumelhart, D. E., Hinton, G. E. & Williams, R. J.”Learning Representations by
Back-Propagating Errors”, Natue, 323, 1986, pp.533-536.