(3.237.97.64) 您好!臺灣時間:2021/03/05 03:57
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:林鈺傑
研究生(外文):Yu-Jie Lin
論文名稱:應用深信網路技術於股票漲跌預測
論文名稱(外文):The Use of Deep Belief Network Technology to Predict the Stock Price Changes
指導教授:陳淑媛陳淑媛引用關係林啟芳
指導教授(外文):Shu-Yuan ChenChi-Fang Lin
口試委員:廖弘源范國清
口試委員(外文):Hong-Yuan Mark LiaoKuo-Chin Fan
口試日期:2017-08-29
學位類別:碩士
校院名稱:元智大學
系所名稱:資訊工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2017
畢業學年度:106
語文別:中文
論文頁數:38
中文關鍵詞:深信網路限制波爾茲曼機器股票預測神經網路
外文關鍵詞:DBNTensorFlow
相關次數:
  • 被引用被引用:0
  • 點閱點閱:139
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
相對於過去,人們對投資越來越重視,如何更好的利用有限的資金成為思考的重點。台灣證卷交易所在民國104年最新統計的股票累計開戶人數超過1,700萬戶,由此可知股票交易在台灣已成為不可或缺的投資管道。股票價格的數據在股票預測市場中提供了一個成功的例子,人工智能(AI)技術例如神經網路(Neuron Network)已被廣泛運用於預測股票價格並輔助投資的策略。然而,傳統的神經網路已被快速發展的深信網路(Deep Belief Network, DBN)在圖像處理和語意辨識等領域上超越,由於深信網路已經發展出幾項純熟的技術可以應用,如何將數量多又複雜的股價資訊做細微且高階抽象的特徵表達,可以利用最近熱門的深信網路來達成。
本論文目的在使用深信網路結合TensorFlow系統進行快速的建模與訓練,幫助投資者可以迅速的將這些股價資訊消化並學習,轉換成對投資者有用的策略。我們主要使用的機器學習模型是深信網路,可以達到高維度的資料特徵表達,並且利用限制波爾茲曼機器從無標記資料裡學習到的資料進行非線性的表示,這是未來深度學習的趨勢,資料的易取性與量多性可以讓我們預想到資料會越來越複雜且充滿雜訊,而昂貴的人工標記資料會越來越稀少,如何從無標記資料訓練出具有高準確度的深信網路,目前還在研究,但本論文之系統在使用較少量的標記資料預測股票漲跌時具有一定準確率的預測能力,且能有效率的建立與訓練深信網路模型。
Compared to the past, people pay more and more attention to investment, how to make better use of limited funds to become the important of thinking. Certificate of exchange in the Taiwan 104 years the latest statistics of the cumulative number of shares of more than 17 million households, we can see that stock trading in Taiwan has become an indispensable investment pipeline. Stock price data provide a successful example in the stock forecast market where artificial intelligence (AI) techniques such as the Neuron Network have been widely used to predict stock prices and assist in investment strategies. However, the traditional neural network has been rapidly developed by the deep belief network (DBN) in image processing and semantic identification and other areas beyond, because the deep belief network has developed a number of skilled technology can be applied, will be more complex price information to do subtle and high-level abstract features of the expression, you can use the recent popular deep belief network to achieve.

The purpose of this paper is to use deep belief network and TensorFlow system for rapid modeling and training to help investors can quickly digest and learn these stock information into a useful strategy for investors. We mainly use the machine learning model is deep belief network can achieve high-dimensional data feature expression, and the use of restricted Boltzmann machine from the non-marked data to learn the non-linear representation, which is the future deep learning Trends. the ease of use of data, and the amount of data can make us predict that the data will be more complex and full of noise, and expensive manual tagging data will become increasingly scarce, how to train from the unmarked data with high accuracy The system is still in the study, but the system of this paper in the use of a smaller amount of marker data to predict the stock when the ups and downs have a certain accuracy of the ability to predict, and the efficient establishment and training deep belief network model.
目錄
摘要 0
目錄 1
圖目錄 3
表目錄 4
第一章、序論 5
1.1 研究背景與動機 5
1.2相關文獻探討 6
1.3研究目標 8
1.4論文架構 9
第二章、深度學習相關技術介紹 9
2.1深度學習基本概念 9
2.2深度學習與神經網路 11
2.3深度學習訓練過程 12
2.4限制波爾茲曼機器 16
2.5深信網路 17
第三章、所提方法 19
3.1系統處理流程 19
3.2資料預處理 20
3.2.1利用相對強弱指標進行股價技術分析 20
3.2.2有標記資料集與無標記資料集建立 24
3.3網路結構設定 24
3.4使用限制波爾茲曼機器建立深信網路 25
3.4.1利用TensorFlow進行快速建模 25
3.4.2 利用非監督式學習提取資料特徵 26
3.4.3 建立深信網路 26
3.5使用監督式學習進行深信網路訓練 27
3.5.1利用監督式學習進行模型訓練 27
3.5.2深信網路訓練 29
3.6績效評估 29
第四章、實驗結果與分析 30
4.1資料來源 30
4.2特徵集合 31
4.3深信網路之參數設定 31
4.4各個目標公司測試資料與驗證資料的預測效果 33
第五章、結論與未來工作 36
5.1結論 36
5.2未來工作 37
參考文獻 38
參考文獻
[1] C. ZHU, J. YIN and Q. LI, "A Stock Decision Support System based on DBNs," Computational Information Systems, pp. 883-893, 15 1 2014.
[2] 吳漢瑞, “應用文字探勘技術於臺灣上市公司重大訊息對股價影響之研究,” 於 國立政治大學資訊管理學系, 碩士學位論文, 2011.
[3] E. F. Fama, "The Behavior of Stock-market Prices," J. Business, vol. 38, pp. 34-105, Jan. 1965.
[4] A. W. Lo and C. A. MacKinlay, A Non-random Walk Down Wall Street, Elizabeth: Princeton University Press, 2002.
[5] W. Zhang, C. Li, Y. Ye, W. Li and E. W. Ngai, "Dynamic Business Network Analysis for Correlated Stock Price Movement Prediction," IEEE Intelligent Systems, vol. 30, pp. 26-33, March 2015.
[6] 蘇珍琦, “應用情感分析技術於台灣股票加權指數預測之研究,” 於 元智大學資訊管理學系, 碩士學位論文, 2013.
[7] R. P. Schumaker and H. Chen, "A Discrete Stock Price Prediction Engine Based on Financial News," IEEE Computer Society, 26 January 2010.
[8] Y. Wang, "Market Index and Stock Price Direction Prediction using Machine," International Journal of Business Intelligence and Data Mining, 2014.
[9] G. E. Hinton, S. Osindero and W. Y. Teh, "A Fast Learning Algorithm for Deep Belief Nets," Neural Computation archive, vol. 18, pp. 1527 - 1554, July 2006.
[10] Zouxy, “Deep Learning(深度学习)学习笔记整理系列之(二),” 08 04 2013. [線上]. Available: http://blog.csdn.net/zouxy09/article/details/8775488. [存取日期: 17 02 2017].
[11] D. H. Hubel and T. N. Wiesel, "Receptive Fields of Single Neurones in the Cat's Striate Cortex," J. Physiol, pp. 574-591, 22 April 1959.
[12] J. Paul and W. Paul, "Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences," in PhD thesis, Harvard University, 1974.
[13] F. Kunihiko , "A Self-organizing Neural Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position," Biol. Cybern., pp. 193-202, 1980.
[14] S. Hochreiter, "Untersuchungen zu Dynamischen Neuronalen Netzen," in Diploma thesis. Institut f. Informatik ,Technische Univ, Munich. Advisor: J. Schmidhuber, 1991.
[15] J. Schmidhuber, "Learning Complex Extended Sequences using the Principle of History Compression," Neural Computation, pp. 234-242, March 1992.
[16] L. Yann, Y. Bengio and G. Hinton, "Deep Learning," nature, pp. 436-444, 28 May 2015.
[17] A. Fischer and C. Igel, "An Introduction to Restricted Boltzmann Machines," Lecture Notes in Computer Science (LNCS), pp. 14-36, 2012.
[18] M. A. H. Dempster, T. W. Payne, Y. Romahi and G. W. P. Thompson, "Computational Learning Techniques for Intraday FX Trading Using Popular Technical Indicators," IEEE Computational Intelligence Society, pp. 744-754, 7 2001.
[19] A. W. Lo and A. C. Mackinlay, "Stock Market Prices do not Follow," Financial Studies, pp. 41-66, 1988.
[20] B. LeBaron, "Technical Trading Rule Profitability and Foreign Exchange Intervention," J. Int. Economics, pp. 124-143, 1999.
[21] C. J. Neely, P. A. Weller and R. Dittmar, "Is Technical Analysis in The Foreign Exchange Market Profitable? A Genetic Programming Approach," J. Financial Quantitative Anal, pp. 405-426, 1997.
[22] M. P. Taylor and H. Allen, "The use of Technical Analysis in the Foreign Exchange Market," J. Int. Money Finance, pp. 304-314, 1992.
[23] M. A. H. Dempster 且 C. M. Jones, “Can Channel Pattern Trading be Successfully Automated?,” European J. Finance, 2001.
[24] R. Gencay, G. Ballocchi, M. Dacorogna, R. Olsen 且 O. Pictet, Real-time Trading Models and the Statistical Properties of Foreign Exchange Rates, Switzerland: Olsen & Associates, 1998.
[25] S. Puitt, W. Richard and E. White, "The CRISMA Trading System: Who Says Technical Analysis Can't Beat the Market?," Journal of Portfolio Management, pp. 55-58, 1988.
[26] 陳應慶, “應用技術分析指標於台灣股票市場加權指數買進時機切入之實證研究 以RSI、MACD及DIF為技術指標,” 於 佛光大學, 碩士論文, 2004.
[27] G. Hinton, A Practical Guide to Training, Toronto: Springer Berlin Heidelberg, 2010.
[28] M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, M. Kudlur, J. Levenberg, R. Monga, S. Moore, D. G. Murray, B. Steiner, P. Tucker, V. Vasudevan, P. Warden, M. Wicke, Y. Yu and X. Zheng, "TensorFlow: A System for Large-Scale Machine Learning," in USENIX Symposium on Operating Systems Design and Implementation, 2016.
[29] 李宏毅, “Introduction of This Course,” 23 09 2016. [線上]. Available: http://speech.ee.ntu.edu.tw/~tlkagk/courses/ML_2016/Lecture/Introduction%20(v4).pdf. [存取日期: 17 02 2017].
[30] G. E. Hinton, P. Dayan, B. J. Frey and R. M. Neal, The "wake-sleep" Algorithm for Unsupervised Neural Networks, Toronto: The American Association for the Advancement of Science, 1995.
電子全文 電子全文(本篇電子全文限研究生所屬學校校內系統及IP範圍內開放)
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔