政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/130988

政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/130988

English | 正體中文 | 简体中文 | Post-Print筆數 : 27 | 全文筆數/總筆數 : 113451/144438 (79%)
造訪人次 : 51248533 線上人數 : 921

RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.

搜尋範圍

查詢小技巧：

您可在西文檢索詞彙前後加上"雙引號"，以獲取較精準的檢索結果

若欲以作者姓名搜尋，建議至進階搜尋限定作者欄位，可獲得較完整資料

進階搜尋

主頁 ‧ 登入 ‧ 上傳 ‧ 說明 ‧ 關於政大典藏 ‧ 管理

到手機版

政大機構典藏 > 商學院 > 金融學系 > 學位論文 > Item 140.119/130988

請使用永久網址來引用或連結此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/130988

題名:	基於神經網路的台指期量化交易策略 Quantitative TAIEX Futures Trading Strategies Based on Neutral Networks
作者:	陸韋廷 Lu, Wei-Ting
貢獻者:	江彌修 Chiang, Mi-Hsiu 陸韋廷 Lu, Wei-Ting
關鍵詞:	神經網路卷積神經網路循環神經網路量化交易台指期 Neural Networks Convolution Neural Networks Recurrent Neural Networks Quantitative Trading Strategies TAIEX Futures
日期:	2020
上傳時間:	2020-08-03 17:37:43 (UTC+8)
摘要:	本研究使用三種不同的神經網路模型，分別為人工神經網路(Artificial Neural Network, ANN)、卷積神經網路(Convolution Neural Networks, CNN)和循環神經網路(Recurrent Neural Networks, RNN)，並將其應用於台灣加權股價指數期貨(台指期)的交易策略開發。本研究比較當輸入資料的資訊含量不同時，對於神經網路模型的輸出結果與交易策略績效所造成的影響。另外也針對三個不同的神經網路模型的輸出結果與交易策略績效進行分析與探討。從實證結果來看，本研究發現不論是使用哪個神經網路模型，在每一個模型中表現最佳的均為使用輸入資訊含量最多的組別，亦即提供更多與預測目標相關的資訊時，這些資訊的確能夠有效提升神經網路模型的訓練結果，並在交易策略的回測獲得更好的報酬與績效。而在本研究使用的三個神經網路模型中，卷積神經網路不論在全樣本或是樣本外均擁有最佳的績效表現。另外，本研究建構的交易策略績效與長期持有大盤績效相比，不論在全樣本或是樣本外時間，績效表現均優於大盤表現。代表神經網路模型確實能夠捕捉到交易標的價格變動的規則，幫助建立具備良好獲利與較佳風險控管能力的交易策略。 In this paper, we implement three neural network models including Artificial Neural Network (ANN), Convolution Neural Networks (CNN) and Recurrent Neural Networks (RNN) in TAIEX Futures quantitative trading strategies. We compare the impact on the performance of trading strategies with different input information. In addition, we analyze the performance of trading strategies with different neural network models. We found that the group with the most input information performs best in each model. Among the three neural network models used in this paper, the performance of Convolution Neural Networks are the best whether they are at all times or testing period. In addition, the performance of the quantitative trading strategies constructed in this study are better than the performance of the benchmark whether they are at all times or testing period. In this paper, we found that the neural network models are useful to build quantitative trading strategies with good performance.
參考文獻:	一、英文參考文獻 [1] Brock W., Lakonishok J., LeBaron B. (1992). Simple Technical Trading Rules and the Stochastic Properties of Stock Returns. The Journal of Finance, Vol. 47, No. 5, 1731-1764. [2] Cho K., Merrienboer B., Gulcehre C., Bahdanau D., Bougares F., Schwenk H., Bengio Y. (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. Association for Computational Linguistics, Pages 1724-1734. [3] Elman J. (1990). Finding structure in time. Cognitive Science, Volume 14, Issue 2, Pages 179-211. [4] Fukushima K. (1980). Neocognitron:A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological Cybernetics. 36 (4): 193–202. [5] Hsu P.H., Hsu Y.C., Kuanc C.M. (2010). Testing the predictive ability of technical analysis using a new stepwise test without data snooping bias. Journal of Empirical Finance, Volume 17, Issue 3, Pages 471-484. [6] Hsu P.H., Taylor M.P. (2016). Technical Trading: Is It Still Beating The Foreign Exchange Market? Journal of International Economics, 102, 188-208. [7] LeCun Y., Boser B., Denker J.S., Henderson D., Howard R.E., Hubbard W., Jackel L.D. (1989) Backpropagation Applied to Handwritten Zip Code Recognition. Neural Computation, 1(4), 541–551. [8] LeCun Y., Bengio Y. (1995). Convolutional Networks for Images, Speech, and Time Series. The Handbook of Brain Theory and Neural Networks, 255-258. [9] Levich R., Thomas L. (1993). The significance of technical trading-rule profits in the foreign exchange market: a bootstrap approach. Journal of International Money and Finance, Volume 12, Issue 5, 451-474. [10] Pruitt S.W., White R.E. (1988). The CRISMA Trading System: Who Says Technical Analysis Can`t Beat The Market? Journal of Portfolio Management, 55-58. [11] Sepp H., Jürgen S. (1997). Long Short-Term Memory. Neural Computation. 9 (8): 1735-1780. [12] Sezer O.B., Ozbayoglu M. (2018). Algorithmic Financial Trading with Deep Convolutional Neural Networks: Time Series to Image Conversion Approach. Applied Soft Computing, Volume 70, Pages 525-538. [13] Warren M., Pitts W. (1943). A Logical Calculus of Ideas Immanent in Nervous Activity. Bulletin of Mathematical Biophysics. 5 (4): 115–133. [14] Werbos P. (1974). Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences. Harvard University, PhD thesis. 二、中文參考文獻 [1] 李杰穎，(2019)。卷積神經網路結合技術指標交易策略在台灣加權指數期貨之運用，國立政治大學，碩士論文。 [2] 許晏寧，(2019)。利用深度強化式學習建構價差交易策略:以台指期與摩台期為例，國立政治大學，碩士論文。 [3] 鄭仁杰，江彌修(2019)。漫步於隨機森林-輔以多數決學習的台股指數期貨交易策略，《經濟論文》，47:3，395-448。 [4] 賴嘉蔚，(2017)。卷積神經網路預測時間序列能力分析，國立政治大學，碩士論文。
描述:	碩士國立政治大學金融學系 107352016
資料來源:	http://thesis.lib.nccu.edu.tw/record/#G0107352016
資料類型:	thesis
DOI:	10.6814/NCCU202000691
顯示於類別:	[金融學系] 學位論文

文件中的檔案:

檔案	描述	大小	格式	瀏覽次數
201601.pdf		4306Kb	Adobe PDF2	0	檢視/開啟

在政大典藏中所有的資料項目都受到原著作權保護.

社群 sharing

著作權政策宣告 Copyright Announcement

1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.

DSpace Software Copyright © 2002-2004 MIT & Hewlett-Packard / Enhanced by NTU Library IR team Copyright © - 回饋