5.1 結論
本研究嘗試運用人工智慧中的多重類神經網路,進行台灣指數期貨的波段走 勢行為之研究,運用多重類神經網路針對短線、長線單一網路來做一個總合評 判,驗證透過長線趨勢是否具有保護短線趨勢的行為能力。經過研究實證發現,
本模式是明顯的比兩組對照組表現的好。本研究提供投資人一個買賣的參考標 準,掌握未來台灣指數期貨的漲跌幅走勢。以下是幾個結論的歸納:
1. 本研究提出的應用多重類神經網路模式適合進行台灣指數期貨的跨日走勢 行為研究,可輔助預測未來的走勢。
2. 單純只用倒傳遞類神經網路的績效表現與預測準確率也是比對照組的隨機 漫步模型表現的好。
3. 對照組的隨機漫步模式獲利能力和預測準確率都比應用多重類神經網路和 單只用倒傳遞類神經網路來的差,從實驗結果可以知道,投資人如果沒有使 用人工智慧方法學輔助其進行投資決策,其所承受的風險損失是相當大的。
5.2 後續建議
由前述章節進行的實驗流程與研究成果,能發現透過本研究應用多重類神經 網路進行波段走勢預測能有穩定的報酬,實已達到本研究的目的,為使本研究之 實驗流程及模型更加完善,提出下列建議,供未來進行進一步延伸研究的建議:
1. 本研究輸入變數較為單純與簡單,未來建議在輸入變數資料方面,可以再加 入其他基本面、技術面、籌碼面等資料,讓模型預測的能力能更穩定與成熟。
2. 可加入一些關於規避風險的方法,對於門檻值的設定可以採用更加嚴格的方 法,避免準確率不夠穩定所產生的大幅損失。
3. 在門檻值的部分,若預測力道較強的可以採加碼買進,反之則是減碼出場,
取代目前模型的最多只能交易一口的限制。
4. 在交易策略方面,目前交易策略為若提前平倉出倉認賠出場的情況下,在下 一個反向訊號出現前均不再作進場動作,未來可針對此部分進行交易策略的 修正,應可增加獲利能力。
46
參考文獻
英文文獻
[1] Bengoechea, A. Glaria., et al., “Stock market indices in Santiago de Chile:
forecasting using neural networks”, IEEE International Conference on Neural Networks , Vol.4, pp. 2172-2175, 1996
[2] Bergerson,K. and Wunsch,D.C. , “A Commodity Trading Model based on a Neural Network-Expert System Hybrid “, IEEE International Joint Conference on Neural Networks, Vol. 1, pp.289-293, 1991
[3] Bessembinder,H. & Chan,K, ”The Profitability of Technical Trading Rules in the Asian Stock Markets”, Pacific-Basin Finance Journal, Vol.3, pp.257-284, 1995
[4] Black,F., ”Noise”, Journal of Finance, Vol.41, pp.529-543, 1986
[5] Blume, L., D. Easley and M. O' Hara., "Market Statistics and Technical Analysis:
The Role of Volume." Journal of Finance 49(1): 153-181, 1994
[6] Brock,W., Lakonishok,J. and LeBaron,B., ”Simple Technical Trading Rules and the Stochastic Properties of Stock Returns”, Journal of Finance, Vol.47,
pp.1731-1764, 1992
[7] Brooks,C. , “Linear and Non-linear (Nor-) Forecastability of High-frequency Exchange Rates”, Journal of Forecasting, Vol.16, pp.125-145, 1997
[8] Casas,C.A.,”Tactical asset allocation:an artificial neural network based model. ” International Joint Conference on Neural Networks, Vol.3, pp.1811-1816, 2001 [9] Davies,P.C.,”Design Issues in Neural Network Development”,NEUROVEST
Journal, Vol.5, pp.21-25, 1994
[10] De Bondt, W., “Betting on Trends: Intuitive Forecasts of Financial Risk and Return,” International Journal of Forecasting 9, pp.355-371, 1993
47
[11] Fama, E. F., "Efficient Capital Markets: a Review of Theory and Empirical Work.” Journal of Finance 25(2), 383-417, 1970
[12] Freeman,J.A. & Skapura,D.M.,”Neural Networks Algorithms,Applications,and Programming Techniques”, New York:Addison-Wesley Publishing Company, 1992
[13] Gencay,R.,”Non-linear Prediction of Security Returns with Moving Average Rules”, Journal of Forecasting, Vol.15, p165-174, 1996
[14] Kahneman,D.& Riepe,M.W.,”Aspects of investor psychology”, Journal of Portfolio Management, Vol.24, pp.52-65, 1998
[15] Kahneman, D., & Tverskey, A., “Prospect theory: An analysis of decision under risk” Econometrica 47, pp.263-291, 1979
[16] Kearns, M., "A Bound on the Error of Cross Validation Using the Approximation and Estimation Rates, with Consequences for the Training-Test Split," Advance in Neural Information Processing System, Vol.8, pp.183-189, 1996.
[17] Kimoto, T. & Asakawa, K. “Stock Market Prediction System with Modular Neural Networks”, IJCNN, Vol.1, pp.I1-I6, 1990
[18] Lapends & Farber, “Nonlinear Signal Processing using Neural Networks:
Prediction andSystem Modeling”, Los Alamos National Laboratory Report, 1987
[19] Levy R.A., “Conceptual Foundation of Technical Analysis”, Financial Analysis Journal, Vol. 12, pp.83-89, 1966
[20] Lui, Y. H. a. D. M., "The use of fundamental and technical analyses by foreign exchange dealers: Hong Kong evidence." Journal of International Money and Finance 17(3): 535-545, 1998
[21] Phua, Paul Kang Hoh, Ming, Daohua, Lin, Weidong, “Neural network with genetically evolved algorithms for stocks prediction”, Asia Pacific Journal of Operational Research, 2001
[22] Refenes, A.P., and Zaidi, A., “Managing Exchange Rate Prediction Strategies
48
with Neural Networks”, Neural Networks in the Capital Markets, pp.213-219, 1995
[23] Reilly F.K., “Investment analysis and portfolio management”, Bryden Press, 1985
[24] Schwärzel, R. & Rosen, B., “Improving the accuracy of financial time series predictiousing multi-neural networks and high order statistics”, International Conference on Neural Networks, 1997
[25] Schwärzel, R., “Prediction of Currency Exchange Rates by Using a Multi-Neural Network System”, Technical Report ISS-15, Department of Business
Administration, Humboldt Universität Berlin, 1995
[26] Shiller,R.J.,”Stock Prices and Social Dynamics”, Brookings Papers on Economic Activity, Vol.2, pp.457-510, 1984
[27] Shleifer,A.”Inefficient Markets:An Introduction to Behavioral Finance”, Oxford University Press, 2000
[28] Shleifer,A.&Robert,W.Vishny, ”A survey of corporate governance”, Journal of Finance, Vol.52, pp.737-783, 1997
[29] Thaler,R.H.,”Mental accounting matters”, Journal of Behavioral Decision Making, Vol.12, pp.183-206, 1999
[30] Vellido,A.,Lisboa,P.J.G., & Vaughan,J.,”Neural Networks in Business a Survey of Applications(1992~1998)”, Journal of Expert System with Application, Vol.17, pp.51-70, 1999
[31] Yoon Youngohc. Swales, George., “Predicting Stock Price Performance: A Neural Network Approach”, Proceedings of the TwentyFourth Annual Hawaii International Conference on System Science, 1991
[32] Zhang,G.,Patuwo,B.E., & Hu,M.Y.,”Forecasting with Artificial Neural Network:The State of the Art”, International Journal of Forecasting, Vol.14, pp.35-62, 1998
49
中文文獻
[33] 林章鈞,「使用類神經網路於台灣貨幣市場匯率趨勢預測之研究」,國立交通 大學資訊管理研究所,碩士論文,1994
[34] 林秀怡,「建構演化是類神經網路於財務時間序列信賴區間動態風險值評價 模型」,交通大學資訊管理所,博士論文,2008
[35] 林聖智,「應用自組織映射圖神經網路與倒傳遞類神經網路於台指選擇權波 動率指數之研究」,國立交通大學資訊管理研究所,碩士論文,2008
[36] 周政宏,「神經網路-理論與實務」,松崗圖書,1995
[37] 胡克非,「應用多重類神經網路於基本面與技術面因素預測新台幣兌美元匯 率」,國立交通大學資訊管理研究所,碩士論文,2007
[38] 張國銘,「美國與台灣股市走勢行為研究-應用自組織映射神經網路與多重類 神經網路」,國立交通大學資訊管理研究所,碩士論文,2008
[39] 陳安斌,「新金融實驗教學之財務金融資訊系統與投資管理」,新陸書局,2005 [40] 葉怡成,「類神經網路模式應用與實作」,儒林圖書有限公司,2003
[41] 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
[42] 鍾仁甫,「技術分析簡單法則於台灣電子個股之應用」,東海大學企業管理研 究所,碩士論文,2001