單層學習神經網路配合多輸出節點應用於期貨預測

The Single-hidden Layer Feedforward Neural Networks with Multiple Output Nodes for Futures Forecast

鄭玉婕(Jheng Yu-Jie)

指導教授 ： 蔡瑞煌

國立政治大學/商學院/資訊管理學系/碩士(2019年)

https://doi.org/10.6814/NCCU201900839

摘要

蔡，許和賴（1998）提出了一種混合人工智能（AI）方法，該方法集成了基於規則的系統和人工神經網絡（ANN）技術，用以預測標準普爾500指數期貨未來價格變化的方向。他們聲稱混合方法可以促進更可靠的智能係統的開發，以模擬專家思維和支持決策過程。
　　這項研究在兩個方面與蔡，許和賴（1998）提出的混合人工智能（AI）有所不同。首先，本研究有兩個新增的狀態變量用於描述市場狀態。其次，我們使用單層前饋式神經網絡（SLFN）和強記、軟化和整合（CSI）學習算法代替推理神經網絡（RN）和反向傳播學習算法。
　　實驗結果表明，所提出的具有CSI學習算法的決策支持系統可有效預測2007年至2013年7年測試期間的Non-obvious和Unobserved的資料。決策支持系統為使用者在做決策時提供建議。

關鍵字

人工神經網絡 ； 強記、 軟化與整合 ； 混合人工智能 ； 期貨預測 ； 決策支持系統

並列摘要

Tsaih, Hsu and Lai (1998) proposed a hybrid artificial intelligence (AI) method that integrates rule-based system techniques and artificial neural network (ANN) techniques to predict the direction of future S&P 500 index futures price changes. They claim that hybrid approaches can facilitate the development of more reliable intelligent systems to simulate expert thinking and support decision-making processes.
　　This study differs from Tsaih, Hsu & Lai (1998) in two ways. First, the study has two additional state variables for the research purpose. Secondly, we use the single hidden layer feedforward neural network (SLFN) and the Cramming, Softening and Integrating (CSI) learning algorithm instead of the Reasoning Neural Networks (RN) and the Back Propagation learning algorithm.
　　The empirical results show that the proposed decision support system with CSI learning algorithm is effective in predicting Non-obvious and Unobserved data during the 7-year test period from 2007 to 2013. The decision support system provides advice to the user when making decisions.

並列關鍵字

Artificial Neural Network ； Cramming and Softening and Integrating ； Hybrid Artificial Intelligence ； Futures Forecast ； Decision Support System

參考文獻

[1] C. Ideenlabor, “Kanon der finanziellen Allgemeinbildung – Ein Memorandum”, in Frankfurt/Main: Commerzbank AG, 2003.

[2] K. Sachse, H. Jungermann and J. Belting, “Investment risk – The perspective of individual investors”, Journal of Economic Psychology, vol. 33, no. 3, pp. 437-447, 2012.

[3] Nosić and M. Weber, “How Riskily Do I Invest? The Role of Risk Attitudes, Risk Perceptions, and Overconfidence”, Decision Analysis, vol. 7, no. 3, pp. 282-301, 2010.

[4] J. D. Schwager, “fundamental analysis, technical analysis, trading, spreads, and options”, in A complete guide to the futures markets, John Wiley & Sons, 1984.

[5] C. Park and S. Irwin, “WHAT DO WE KNOW ABOUT THE PROFITABILITY OF TECHNICAL ANALYSIS? ”, Journal of Economic Surveys, vol. 21, no. 4, pp. 786-826, 2007.