學術產出-Theses
Article View/Open
Publication Export
-
題名 深度投資組合：以臺灣50爲例
Deep Portfolio: the Evidence in Taiwan 50作者 張玄
Zhang, Xuan貢獻者 廖四郎
張玄
Zhang, Xuan關鍵詞 神經網路
長短期記憶體
自編碼器
深度投資組合
Neural networks
LSTM
Autoencoder
Deep portfolio
ETF日期 2019 上傳時間 7-Aug-2019 16:12:55 (UTC+8) 摘要 神經網路因其强大的對特徵提取能力，近年來廣泛的應用在金融領域，如資產定價、風險管理、投資組合構建。與傳統的投資組合理論相比，神經網路可以對數據閒複雜的非綫性特徵更爲敏感；此外，更容易通對樣本外驗證防止模型過擬合。在本研究中，通過神經網路對臺灣50指數與其成分股完成選股和構造投資組合追蹤臺灣50指數，實現用較少的股票數量達到采用完全複製發的元大0050ETF追蹤誤差。
Neural networks have been applied to financial applications more recently, such as asset pricing, risk management and constructing portfolios. Compared with standard financial methods only capture the linearity of data, the neural networks can take more non-linearity into account. Another advantage of neural network is that it is easier to reduce over-fitting and improve the performance on the validation set. In this study we use dense and LSTM neural networks to select stocks from stock universe and construct a portfolio to track Taiwan 50 Index. The result shows that deep portfolio with less stocks can have less tracking error than a fully replicated ETF (Yuanta 0050).參考文獻 Asness, C. S., Ilmanen, A., Israel, R., and Moskoqitz, T. J. (1998). Investing with Style.Journal of Investment Management, 13(11), 27-63.Black, F., & Litterman, R. (1992). Global portfolio optimization. Financial analysts journal, 48(5), 28-43.Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity. Journal of econometrics, 31(3), 307-327.Chamberlain, G. and Rothschild, M. (1983). Arbitrage, Factor Structure and Mean-Variance analysis in Large Asset markets. Econometrika, 51, 1205-24.Cho, K., Van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078.Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555.Cybenko, G. (1989). Approximation by superpositions of a sigmoidal function. Mathematics of control, signals and systems, 2(4), 303-314.Duchi, J., Hazan, E., & Singer, Y. (2011). Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12(Jul), 2121-2159.Elman, J. L. (1990). Finding structure in time. Cognitive science, 14(2), 179-211.Fama, E. F., & French, K. R. (2012). Size, value, and momentum in international stock returns. Journal of financial economics, 105(3), 457-472.Glorot, X., Bordes, A., & Bengio, Y. (2011, June). Deep sparse rectifier neural networks. In Proceedings of the fourteenth international conference on artificial intelligence and statistics (pp. 315-323).Graves, A. Supervised sequence labelling with recurrent neural networks. 2012.Greff, K., Srivastava, R. K., Koutník, J., Steunebrink, B. R., & Schmidhuber, J. (2016). LSTM: A search space odyssey. IEEE transactions on neural networks and learning systems, 28(10), 2222-2232.Heaton, J. B., Polson, N. G., & Witte, J. H. (2017). Deep learning for finance: deep portfolios. Applied Stochastic Models in Business and Industry, 33(1), 3-12.Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing the dimensionality of data with neural networks. science, 313(5786), 504-507.Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural networks, 2(5), 359-366.Jegadeesh, N., & Titman, S. (1993). Returns to buying winners and selling losers: Implications for stock market efficiency. The Journal of finance, 48(1), 65-91.Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.LeCun, Y. A., Bottou, L., Orr, G. B., & Müller, K. R. (2012). Efficient backprop. In Neural networks: Tricks of the trade (pp. 9-48). Springer, Berlin, Heidelberg.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.Markowitz, H. (1952). Portfolio selection. The journal of finance, 7(1), 77-91.McCulloch, W. S., & Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5(4), 115-133.Rosenblatt, F. (1958). The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review, 65(6), 386.Ross, S. (1976). The Arbitrage Theory and Capital Asset Pricing. J. Economic Theory, 13,341-360.Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1988). Learning representations by back-propagating errors. Cognitive modeling,Sharpe, W. F. (1964). Capital asset prices: A theory of market equilibrium under conditions of risk. The journal of finance, 19(3), 425-442.Sharpe, W. F. (1992). Asset allocation: Management style and performance measurement.Sims, C. A. (1980). Macroeconomics and reality. Econometrica: journal of the Econometric Society, 1-48.Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P. A. (2008, July). Extracting and composing robust features with denoising autoencoders. In Proceedings of the 25th international conference on Machine learning (pp. 1096-1103). ACM.李存修, & 尤亭歡. (2015). 臺灣, 香港, 中國大陸三地 ETF 追蹤誤差之研究. 兩岸金融季刊, 3(1), 1-22. 描述 碩士
國立政治大學
金融學系
106352041資料來源 http://thesis.lib.nccu.edu.tw/record/#G0106352041 資料類型 thesis dc.contributor.advisor 廖四郎 zh_TW dc.contributor.author (Authors) 張玄 zh_TW dc.contributor.author (Authors) Zhang, Xuan en_US dc.creator (作者) 張玄 zh_TW dc.creator (作者) Zhang, Xuan en_US dc.date (日期) 2019 en_US dc.date.accessioned 7-Aug-2019 16:12:55 (UTC+8) - dc.date.available 7-Aug-2019 16:12:55 (UTC+8) - dc.date.issued (上傳時間) 7-Aug-2019 16:12:55 (UTC+8) - dc.identifier (Other Identifiers) G0106352041 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/124740 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 金融學系 zh_TW dc.description (描述) 106352041 zh_TW dc.description.abstract (摘要) 神經網路因其强大的對特徵提取能力，近年來廣泛的應用在金融領域，如資產定價、風險管理、投資組合構建。與傳統的投資組合理論相比，神經網路可以對數據閒複雜的非綫性特徵更爲敏感；此外，更容易通對樣本外驗證防止模型過擬合。在本研究中，通過神經網路對臺灣50指數與其成分股完成選股和構造投資組合追蹤臺灣50指數，實現用較少的股票數量達到采用完全複製發的元大0050ETF追蹤誤差。 zh_TW dc.description.abstract (摘要) Neural networks have been applied to financial applications more recently, such as asset pricing, risk management and constructing portfolios. Compared with standard financial methods only capture the linearity of data, the neural networks can take more non-linearity into account. Another advantage of neural network is that it is easier to reduce over-fitting and improve the performance on the validation set. In this study we use dense and LSTM neural networks to select stocks from stock universe and construct a portfolio to track Taiwan 50 Index. The result shows that deep portfolio with less stocks can have less tracking error than a fully replicated ETF (Yuanta 0050). en_US dc.description.tableofcontents 第一章 緒論 1第一節 研究動機 1第二節 研究目的 2第三節 研究背景與文獻回顧 3一、 深度學習 3二、 時間序列 3三、 資產組合與資產定價理論 4第二章 研究方法 6第一節 神經網絡構架 6一、 一般前饋式(feed-forward)神經網路 6二、 神經網路結構和單元 8第二節 神經網路訓練與優化 16一、 訓練神經網路 16二、 神經網路參數更新 19第三節 神經網路數據處理 24一、 特徵標準化/歸一化 24二、 LSTM 輸入數據重構 24第四節 選股與投資組合構建 25一、 選股依據 25二、 構造投資組合 26第三章 實證結果 27第一節 研究對象 27第二節 自編碼器去噪聲及選股 29一、 Dense-AE 模型去噪聲結果 29二、 LSTM-AE 模型去噪聲結果 31三、 Dense-AE與LSTM-AE對比與選股 33第三節 投資組合校準(calibration)及驗證(validation) 35一、 投資組合校準(calibration) 35二、 投資組合驗證(validation) 36第四章 結論與展望 38第一節 結論 38第二節 未來展望 38附錄 40自編碼神經網路重構誤差列表 40參考文獻 43 zh_TW dc.format.extent 2669248 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0106352041 en_US dc.subject (關鍵詞) 神經網路 zh_TW dc.subject (關鍵詞) 長短期記憶體 zh_TW dc.subject (關鍵詞) 自編碼器 zh_TW dc.subject (關鍵詞) 深度投資組合 zh_TW dc.subject (關鍵詞) Neural networks en_US dc.subject (關鍵詞) LSTM en_US dc.subject (關鍵詞) Autoencoder en_US dc.subject (關鍵詞) Deep portfolio en_US dc.subject (關鍵詞) ETF en_US dc.title (題名) 深度投資組合：以臺灣50爲例 zh_TW dc.title (題名) Deep Portfolio: the Evidence in Taiwan 50 en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) Asness, C. S., Ilmanen, A., Israel, R., and Moskoqitz, T. J. (1998). Investing with Style.Journal of Investment Management, 13(11), 27-63.Black, F., & Litterman, R. (1992). Global portfolio optimization. Financial analysts journal, 48(5), 28-43.Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity. Journal of econometrics, 31(3), 307-327.Chamberlain, G. and Rothschild, M. (1983). Arbitrage, Factor Structure and Mean-Variance analysis in Large Asset markets. Econometrika, 51, 1205-24.Cho, K., Van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078.Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555.Cybenko, G. (1989). Approximation by superpositions of a sigmoidal function. Mathematics of control, signals and systems, 2(4), 303-314.Duchi, J., Hazan, E., & Singer, Y. (2011). Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12(Jul), 2121-2159.Elman, J. L. (1990). Finding structure in time. Cognitive science, 14(2), 179-211.Fama, E. F., & French, K. R. (2012). Size, value, and momentum in international stock returns. Journal of financial economics, 105(3), 457-472.Glorot, X., Bordes, A., & Bengio, Y. (2011, June). Deep sparse rectifier neural networks. In Proceedings of the fourteenth international conference on artificial intelligence and statistics (pp. 315-323).Graves, A. Supervised sequence labelling with recurrent neural networks. 2012.Greff, K., Srivastava, R. K., Koutník, J., Steunebrink, B. R., & Schmidhuber, J. (2016). LSTM: A search space odyssey. IEEE transactions on neural networks and learning systems, 28(10), 2222-2232.Heaton, J. B., Polson, N. G., & Witte, J. H. (2017). Deep learning for finance: deep portfolios. Applied Stochastic Models in Business and Industry, 33(1), 3-12.Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing the dimensionality of data with neural networks. science, 313(5786), 504-507.Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural networks, 2(5), 359-366.Jegadeesh, N., & Titman, S. (1993). Returns to buying winners and selling losers: Implications for stock market efficiency. The Journal of finance, 48(1), 65-91.Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.LeCun, Y. A., Bottou, L., Orr, G. B., & Müller, K. R. (2012). Efficient backprop. In Neural networks: Tricks of the trade (pp. 9-48). Springer, Berlin, Heidelberg.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.Markowitz, H. (1952). Portfolio selection. The journal of finance, 7(1), 77-91.McCulloch, W. S., & Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5(4), 115-133.Rosenblatt, F. (1958). The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review, 65(6), 386.Ross, S. (1976). The Arbitrage Theory and Capital Asset Pricing. J. Economic Theory, 13,341-360.Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1988). Learning representations by back-propagating errors. Cognitive modeling,Sharpe, W. F. (1964). Capital asset prices: A theory of market equilibrium under conditions of risk. The journal of finance, 19(3), 425-442.Sharpe, W. F. (1992). Asset allocation: Management style and performance measurement.Sims, C. A. (1980). Macroeconomics and reality. Econometrica: journal of the Econometric Society, 1-48.Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P. A. (2008, July). Extracting and composing robust features with denoising autoencoders. In Proceedings of the 25th international conference on Machine learning (pp. 1096-1103). ACM.李存修, & 尤亭歡. (2015). 臺灣, 香港, 中國大陸三地 ETF 追蹤誤差之研究. 兩岸金融季刊, 3(1), 1-22. zh_TW dc.identifier.doi (DOI) 10.6814/NCCU201900192 en_US
