Responsive image
博碩士論文 etd-0525118-232624 詳細資訊
Title page for etd-0525118-232624
論文名稱
Title
以深度學習建構Smart Beta交易策略:以臺灣股票市場為例
Constructing Smart Beta Trading Strategies with Deep Learning: Evidence from Taiwan Stock Market
系所名稱
Department
畢業學年期
Year, semester
語文別
Language
學位類別
Degree
頁數
Number of pages
112
研究生
Author
指導教授
Advisor
召集委員
Convenor
口試委員
Advisory Committee
口試日期
Date of Exam
2018-06-25
繳交日期
Date of Submission
2018-06-25
關鍵字
Keywords
Smart Beta、股票市場預測、卷積神經網路、多層感知器、深度學習
Stock Market Prediction, Smart Beta, Convolutional Neural Networks, Deep Learning, Multilayer Perceptron
統計
Statistics
本論文已被瀏覽 5819 次,被下載 26
The thesis/dissertation has been browsed 5819 times, has been downloaded 26 times.
中文摘要
本論文以深度學習中的多層感知器(Multilayer Perceptron, MLP)和卷積神經網路(Convolutional Neural Networks, CNN)為投資模型架構,並搭配Smart Beta因子與技術指標來建來構出深度學習策略基金,目的是要驗證深度學習模型在金融交易領域上是否有良好的表現。
每季進行模型的更新及訓練,投資組合標的更新則以季頻和月頻兩種方式來分別探討,在設定貼近實務交易的條件限制下,以台灣加權指數和標杆投資組合為比較基準,針對2007年到2017年的台灣股票市場來進行相關績效回測。
從季頻更新之投資組合結果可發現,深度學習策略基金的績效表現除了能穩健優於台灣加權指數,最終績效也高於標杆投資組合。此外,透過特徵篩選法讓輸入特徵更為精煉的情況下,可使得深度學習策略基金的績效再更進一步提升。
在月頻更新之投資組合下,可以發現透過月報資料來即時更新投資組合持有標的可以使整體績效再進一步提升。從最佳績效的投資組合來看,其年化報酬率可達到20.49%、年化夏普比率也高達116.48%,驗證深度學習模型在基金建構之實務交易上有其可行性存在。
最後,也針對大規模資金下的深度學習策略基金進行穩健性評估,從結果可發現績效還是能穩定優於台灣加權指數及標杆投資組合,可驗證深度學習策略基金不會因為較大資金而使績效有急遽下滑的現象。
Abstract
In this research, Multilayer Perceptron (MLP) and Convolutional Neural Networks (CNN), belonging to Deep Learning, are designed as the investment models. Using Smart Beta factors and technical indicators as model inputs, this paper provides a Deep Learning Strategy Fund strategies.
The purpose of this research is to verify whether the deep learning model performs well in the field of financial trading.

The followings are the model settings: (1) The frequency of updating and training deep learning model is quarter base. (2)The rebalance of the deep learning portfolio is discussed separately in terms of quarterly frequency or monthly frequency. (3) Taiwan Weighted Index and benchmark portfolio based on Asness(2017) are used as comparing standards with deep learning strategy fund.
Under conditions of model settings, the practical trading rules and benchmark standards, using Taiwan stock market as research data, this paper backtests related fund performance from 2007 to 2017.

Based on the results of the quarterly balance of the portfolio, it can be seen that the performance of the Deep Learning Strategy Funds is better than the Taiwan Weighted Index, and the final cumulative return is also higher than the benchmark portfolio. In addition, through the feature filter method, the input factors can be refined well, which can further enhance the performance of the Deep Learning Strategy Funds.
Under the monthly rebalance of the portfolio, it can be seen that the portfolios updated through the monthly revenue report can further enhance the overall performance compared with quarterly balance of the portfolios. Take the best-performing portfolio as a example, it’s annual return can up to 20.49%, and it’s annual Sharpe ratio is also as high as 116.48%. This result can verify the fact that the Deep Learning model has its feasibility in the practice of fund construction.
Finally, the research also conducts a robust test of the Deep Learning Strategy Funds under large-scale fund. From the results, it can be found that the performance is still better than Taiwan Weighted Index and benchmark portfolio. This result also verify that Deep Learning Strategy Funds can not be influenced largely due to large-scale fund.
目次 Table of Contents
論文審定書 i
誌謝 ii
摘要 iii
Abstract iv
第一章 緒論 1
第一節 研究背景與動機 1
第二節 研究目的 2
第三節 研究流程與架構 4
第二章 文獻探討 5
第一節 特徵因子 5
第二節 深度學習演算法 9
第三章 研究方法 12
第一節 模型建構之流程步驟 12
第二節 樣本資料說明 13
第三節 Smart Beta因子與技術指標之定義及說明 13
第四節 深度學習演算法介紹及流程架構 17
第五節 Smart Beta因子與技術指標搭配深度學習之投資組合建構 28
第六節 績效指標介紹 42
第四章 實證結果 44
第一節 資料來源及說明 44
第二節 未採用深度學習之標杆投資組合建構 44
第三節 深度學習模型之有效性評估 45
第四節 績效回測結果與分析 48
第五章 結論與建議 85
第一節 結論 85
第二節 後續研究與建議 86
參考文獻 89
附錄A 特徵因子之使用及計算方式 93
參考文獻 References
外文文獻
1. Altman, Edward I. 1968. "Financial Ratios, Discriminant Analysis and the Prediction of Corporate Bankruptcy." The Journal of Finance 23, no.4: 589-609.
2. Amihud, Y. 2002. "Illiquidity and Stock Returns: Cross-Section and Time-Series Effects." Journal of Financial Markets. 5, no.1: 31-56.
3. Asness, Clifford S, Andrea Frazzini and Lasse Heje Pedersen. 2017. "Quality Minus Junk." Available at SSRN 2312432, AQR Capital Management.
4. B. Marshall, M. Young and L. Rose. 2006. "Candlestick technical trading strategies: Can they create value for investors?" Journal of Banking and Finance. 30, no.8: 2303-2323
5. Carhart, M. M. 1997. "On Persistence in Mutual Fund Performance." The Journal of Finance. 52: 57-82
6. Chang, Y. Y., Faff, R., and Hwang, C. Y. 2010. "Liquidity and Stock Returns in Japan: New Evidence." Pacific-Basin Finance Journal. 18, no.1: 90-115.
7. Chong, TT-L and Ng, W-K. 2008. "Technical analysis and the London stock exchange: testing the MACD and RSI rules using the FT30." Applied Economics Letters. 15: 1111-1114.
8. Cready, W., Lopez, T. J., and Sisneros, C. A. 2010. "The Persistence and Market Valuation of Recurring Nonrecurring Items." The Accounting Review. 85, no.5: 1577-1615.
9. D. Kingma and J. Ba. 2015. "Adam: A method for stochastic optimization." ICLR.
10. DeMiguel V, Garlappi L and Uppal R. 2009. "Optimal versus naive diversification: how inefficient is the 1/N strategy? " Review of Financial Studies. 22, no.5: 1915-1953.
11. Chong, C. Han, and F. C. Park. 2017. "Deep learning networks for stock market analysis and prediction: Methodology, data representations, and case studies." Expert Systems with Applications. 83: 187–205.
12. E. Essaadi, J. Jouini and W. Khallouli. 2009. "The Asian crisis contagion: a dynamic correlation approach analysis." Panoeconomicus. 56: 241-260
13. Fama, E.F. and K. French. 1992. "The CrossSection of Expected Stock Return." Journal of Finance. 47: 427-465.
14. Frazzini, Andrea and Lasse Heje Pedersen. 2014."Betting against Beta." Journal of Financial Economics. 111, no. 1: 1-25.
15. H. Yu, G.V. Nartea, C. Gan and L.J. Yao. 2013. "Predictive ability and profitability of simple technical trading rules: Recent evidence from Southeast Asian stock markets." International Review of Economics & Finance. 25: 356-371
16. Hakan Gunduz, Yusuf Yaslan and Zehra Cataltepe. 2017."Intraday prediction of Borsa Istanbul using convolutional neural networks and feature correlations." Knowledge-Based Systems. 137: 138-148.
17. J. Christopher Hughen and Jack Strauss. 2017. "Portfolio Allocations Using Fundamental Ratios: Are Profitability Measures More Effective in Selecting Firms and Sectors?" The Journal of Portfolio Management. 87-101.
18. Jensen, Michael C, Fischer Black and Myron S Scholes. 1972." The Capital Asset Pricing Model: Some Empirical Tests." Studies in the Theory of Capital Markets.
19. K. Anderson and C. Brooks. 2006. "The long-term price-earnings ratio." Journal of Business Finance & Accounting. 33: 1063-1086
20. Krizhevsky, I. Sutskever, and G. Hinton. 2012. "Imagenet classification with deep convolutional neural networks." In NIPS.
21. K. He, X. Zhang, S. Ren, and J. Sun. 2015. "Delving deep into rectifiers: Surpassing human-level performance on imagenet classification." In ICCV.
22. M. Ratner and R. Leal. 1999. "Tests of Technical Trading Strategies in the Emerging Equity Markets of Latin America and Asia." Journal of Banking & Finance. 23, no.5: 1881-1905.
23. Nguyen Hoang Hung .2016. "Various moving average convergence divergence trading strategies: a comparison." Investment Management and Financial Innovations. 13, no.2.
24. Omer Berat Sezer , Murat Ozbayoglu and Erdogan Dogdu. 2017. "A Deep Neural-Network Based Stock Trading System Based on Evolutionary Optimized Technical Analysis Parameters." Procedia Computer Science. 114, no.3: 473-480.
25. P. Murugan. 2017. "Feed forward and backward run in deep convolution neural network." arXiv preprint. 1711.03278.
26. Rosenblatt, Frank. 1961. "Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms." Spartan Books, Washington DC.
27. Rumelhart, D.E., Hinton, G.E., and Williams, R.J. 1986. "Learning internal representations by backpropagating errors." Nature. 323: 533-536.
28. Rumelhart, David E., Hinton, Geoffrey E., Williams and Ronald J. 1986. "Learning representations by back-propagating errors." Nature. 323 (6088): 533-536.
29. R. Ball, J. Gerakos, J.T. Linnainmaa and V.V. Nikolaev. 2016. "Accruals, cash flows, and operating profitabilty in the cross section of stock returns." Journal of Financial Economics. 121: 28-45.
30. Sharpe and William F. 1964."Capital Asset Prices: A Theory of Market Equilibrium under Conditions of Risk." The Journal of Finance. 19, no. 3: 425-442.
31. Sloan, R. 1996. "Do stock prices fully reflect information in accruals and cash flows about future earnings?" The Accounting Review. 71: 289-315.
32. Tukey, J. W. 1977. "Exploratory data analysis." Reading, PA: Addison-Wesley.

中文文獻
1. 陳鄢貞(2011),以財務指標及技術指標建構股價預測模型-類神經網路模型之應用,臺北大學國際財務金融在職專班學位論文
2. 陳緯新(2012),重複發生非經常性項目的盈餘持續性和股價之關聯性-以台灣上市公司為例,臺灣大學會計學研究所學位論文
3. 盧泰源 (2016),最適化Smart Beta策略組合型基金之應用-以台灣股票市場之交易策略研究,中山大學財務管理研究所學位論文
4. 黃君平(2016),基於深度學習概念之金融市場價格預測,交通大學資訊管理研究所學位論文
5. 陳俊豪(2017),利用卷積神經網路深度學習方法預測外匯走勢,臺灣大學經濟學研究所學位論文
電子全文 Fulltext
本電子全文僅授權使用者為學術研究之目的,進行個人非營利性質之檢索、閱讀、列印。請遵守中華民國著作權法之相關規定,切勿任意重製、散佈、改作、轉貼、播送,以免觸法。
論文使用權限 Thesis access permission:自定論文開放時間 user define
開放時間 Available:
校內 Campus: 已公開 available
校外 Off-campus: 已公開 available


紙本論文 Printed copies
紙本論文的公開資訊在102學年度以後相對較為完整。如果需要查詢101學年度以前的紙本論文公開資訊,請聯繫圖資處紙本論文服務櫃台。如有不便之處敬請見諒。
開放時間 available 已公開 available

QR Code