跳到主要內容

臺灣博碩士論文加值系統

(44.210.149.205) 您好!臺灣時間:2024/04/12 21:42
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

: 
twitterline
研究生:陳彥安
研究生(外文):Chen, Yen-An
論文名稱:深度學習於台股動態投資組合之應用
論文名稱(外文):Application of Deep Learning for Dynamic Portfolio of Taiwan Stock Market
指導教授:戴天時戴天時引用關係
指導教授(外文):Dai, Tian-Shyr
口試委員:林士貴劉亮志黃宜侯戴天時
口試委員(外文):Lin, Shih-KueiLiu, Liang-chihHuang, Yi-HouDai, Tian-Shyr
學位類別:碩士
校院名稱:國立交通大學
系所名稱:管理學院財務金融學程
學門:商業及管理學門
學類:財務金融學類
論文種類:學術論文
論文出版年:2019
畢業學年度:108
語文別:中文
論文頁數:57
中文關鍵詞:機器學習深度學習神經網路長短期記憶三大法人時間序列最佳投資組合
外文關鍵詞:Machine learningDeep learningNeural networkLSTMInstitutional investorTime seriesOptimal portfolio
相關次數:
  • 被引用被引用:7
  • 點閱點閱:1121
  • 評分評分:
  • 下載下載:359
  • 收藏至我的研究室書目清單書目收藏:6
本研究使用長短期記憶區塊(LSTM)架構而成之深度神經網路分析選定投資標的之三大法人每日買賣超的籌碼變化,以捕捉此時間序列資料中隱含之訊號,進而學習得到動態調整投資組合之能力以提高投資報酬。實驗結果顯示,訓練後模型能依三大法人每日買賣超籌碼變化情形,主動地動態調整投資組合權重,整體而言,投資績效表現優於臺灣50指數及Markowitz均值-方差模型之效率前緣上Sharpe Ratio最大之最佳投資組合。
This study uses deep neural network composed of Long Short-Term Memory (LSTM) to analyze the daily changes of institutional investors’ holding allocation for capturing implicit signals in these time series datasets and learning how to adjust portfolio. According to the results of experiments, the trained model can dynamically adjust portfolio initiatively based on the daily changes of institutional investors’ holding allocation. In general, the performance of the trained LSTM model surpasses the performance of Taiwan 50 Index and optimal portfolio with the highest Sharpe ratio on Markowitz’s efficient frontier.
摘要 i
ABSTRACT ii
誌謝 iii
目錄 iv
表目錄 v
圖目錄 vi
第一章 緒論 1
1.1 研究背景 1
1.2 研究動機與目的 2
1.3 研究流程 2
1.4 論文架構 3
第二章 文獻回顧與背景知識 4
2.1 文獻回顧 4
2.2 深度學習相關背景知識 5
2.3 深度學習軟體套件 13
第三章 研究方法 14
3.1 資料來源及範圍 14
3.2 投資標的選擇方法 14
3.3 訓練資料前處理方式 15
3.4 深度學習模型架構 18
第四章 實驗結果與分析 24
第五章 結論與建議 28
參考文獻 30
附錄一 33
[1] 王釗東(2017),「以大數據探究財經新聞對台灣股票市場表現之影響」,國立臺灣大學新聞研究所,碩士論文。
[2] 王宥杰(2018),「應用深度學習探索網路輿論與股價變動相關性之研究—以PTT為例」,東吳大學資訊管理學系,碩士論文。
[3] 白傑任(2017),「利用籌碼面分析與隨機森林建構最適投資組合」,國立政治大學風險管理與保險學系,碩士論文。
[4] 林可依(2003),「台灣上市股市三大法人買賣超是否可提供投資人短期獲利機會?」,國立東華大學國際經濟研究所,碩士論文。
[5] 范聖培(2014),「三大法人之買賣超行為對股價短期報酬之研究」,國立中央大學財務金融學系在職專班,碩士論文。
[6] 范姜賀嵩(2018),「應用時間序列與機器學習預測股票最佳化投資組合」,國立嘉義大學資訊管理學系研究所,碩士論文。
[7] 陳詩文(2014),「利用類神經網路預測標準普爾500指數及台灣金融股票指數」,國立高雄海洋科技大學電訊工程研究所,碩士論文。
[8] 張家瑋(2017),「利用籌碼面分析與關聯規則建構最適投資組合」,國立政治大學風險管理與保險學系,碩士論文。
[9] 盧陽正, 翁振益, 及方豪(2008),「臺灣股市三大法人持股調整, 群聚效應, 回饋交易, 串流行為與群聚之動量持續性」,管理與系統 15.4: 523-543。
[10] Barber, Brad M., et al. “Just How Much Do Individual Investors Lose by Trading?” Review of Financial Studies, vol. 22, no. 2, 2008, pp. 609–632., doi:10.1093/rfs/hhn046.
[11] Duchi, John, Elad Hazan, and Yoram Singer. "Adaptive subgradient methods for online learning and stochastic optimization." Journal of Machine Learning Research 12.Jul (2011): 2121-2159.
[12] Fischer, Thomas, and Christopher Krauss. “Deep Learning with Long Short-Term Memory Networks for Financial Market Predictions.” European Journal of Operational Research, vol. 270, no. 2, 2018, pp. 654–669., doi:10.1016/j.ejor.2017.11.054.
[13] Ferri, C., et al. “An Experimental Comparison of Performance Measures for Classification.” Pattern Recognition Letters, vol. 30, no. 1, 2009, pp. 27–38., doi:10.1016/j.patrec.2008.08.010.
[14] Falas, T., and A.-G. Stafylopatis. “The Impact of the Error Function Selection in Neural Network-Based Classifiers.” IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339), doi:10.1109/ijcnn.1999.832651.
[15] Grinblatt, Mark, et al. “Momentum Investment Strategies, Portfolio Performance, and Herding: A Study of Mutual Fund Behavior.” The American Economic Review, vol. 85, no. 5, 1995, pp. 1088–1105. JSTOR, www.jstor.org/stable/2950976.
[16] Gers, Felix A., et al. “Learning to Forget: Continual Prediction with LSTM.” 9th International Conference on Artificial Neural Networks: ICANN '99, 1999, pp. 850–855., doi:10.1049/cp:19991218.
[17] Graves, Alex. Supervised Sequence Labelling with Recurrent Neural Networks. Springer, 2012.
[18] Graves, Mohamed and Hinton, "Speech recognition with deep recurrent neural networks," 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, 2013, pp. 6645-6649. doi: 10.1109/ICASSP.2013.6638947.
[19] Golik, Pavel, et al. “Cross-Entropy vs. Squared Error Training: a Theoretical and Experimental Comparison.” INTERSPEECH-2013, 2013, pp. 1756–1760.
[20] Hsieh, Shu-Fan. “Individual and Institutional Herding and the Impact on Stock Returns: Evidence from Taiwan Stock Market.” International Review of Financial Analysis, vol. 29, 2013, pp. 175–188., doi:10.1016/j.irfa.2013.01.003.
[21] Heaton, J. B., et al. “Deep Learning for Finance: Deep Portfolios.” Applied Stochastic Models in Business and Industry, vol. 33, no. 1, 2017, pp. 3–12., doi:10.1002/asmb.2209.
[22] Hochreiter, Sepp, and Jürgen Schmidhuber. “Long Short-Term Memory.” Neural Computation, vol. 9, no. 8, 1997, pp. 1735–1780., doi:10.1162/neco.1997.9.8.1735.
[23] Hermans, Michiel, and Benjamin Schrauwen. “Training and Analysing Deep Recurrent Neural Networks.” Advances in Neural Information Processing Systems 26, Curran Associates, Inc., 2013, pp. 190–198.
[24] Kriegeskorte, Nikolaus, and Tal Golan. “Neural Network Models and Deep Learning.” Current Biology, vol. 29, no. 7, 2019, doi:10.1016/j.cub.2019.02.034.
[25] Karpathy, Andrej. “The Unreasonable Effectiveness of Recurrent Neural Networks.” Andrej Karpathy Blog, 21 May 2015, karpathy.github.io/2015/05/21/rnn-effectiveness/.
[26] Kingma, Diederik P., and Jimmy Ba. "Adam: A method for stochastic optimization." arXiv preprint arXiv:1412.6980 (2014).
[27] Lecun, Yann, et al. “Deep Learning.” Nature, vol. 521, no. 7553, 2015, pp. 436–444., doi:10.1038/nature14539.
[28] Markowitz, Harry. “Portfolio Selection.” The Journal of Finance, vol. 7, no. 1, 1952, p. 77., doi:10.2307/2975974.
[29] Nofsinger, John R., and Richard W. Sias. “Herding and Feedback Trading by Institutional and Individual Investors.” The Journal of Finance, vol. 54, no. 6, 1999, pp. 2263–2295., doi:10.1111/0022-1082.00188.
[30] Ruder, Sebastian. “An Overview of Gradient Descent Optimisation Algorithms.” ArXiv Preprint ArXiv:1609.04747, 2016.
[31] Troiano, Luigi, et al. “Replicating a Trading Strategy by Means of LSTM for Financial Industry Applications.” IEEE Transactions on Industrial Informatics, vol. 14, no. 7, 2018, pp. 3226–3234., doi:10.1109/tii.2018.2811377.
[32] Tieleman, Tijmen, and Geoffrey Hinton. "Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude." COURSERA: Neural networks for machine learning 4.2 (2012): 26-31.
[33] Wikipedia contributors. "Gradient descent." Wikipedia, The Free Encyclopedia. Wikipedia, The Free Encyclopedia, 5 Jun. 2019. Web. 9 Jun. 2019, https://en.wikipedia.org/wiki/Gradient_descent.
[34] Yan, Xuemin (Sterling), and Zhe Zhang. “Institutional Investors and Equity Returns: Are Short-Term Institutions Better Informed?” Review of Financial Studies, vol. 22, no. 2, 2007, pp. 893–924., doi:10.1093/revfin/hhl046.
[35] Zeiler, Matthew D. "ADADELTA: an adaptive learning rate method." arXiv preprint arXiv:1212.5701 (2012).
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
無相關期刊