Many scholars have attempted to find the factors that have a pattern of performance and bring profit to investors from an empirical perspective by quantifying multi-factor models. In addition to factor stock selection, some literature tried to combine timing strategy to improve investment performance. Therefore, this research refers to the quantitative selection model proposed by Zhuo, Yu-Chen and redesign the architecture. Make the model have a mechanism for switching between countries. To verify stock selection performance of the financial factor on U.S. stocks and also testing weather technical strategy could improve profit or risk consistency.
This research’s backtesting system is built in Python to make the system more flexible in terms of expansion. The system uses seven single-factor and three dual-factor to test the effectiveness of financial factor stock selection in today's U.S. stock. It also using buy-and-hold, inverse Bollinger Bands, bargaining hunting, and inverse high-low
channels to test whether the technical strategies have a consistent impact on performance. In addition to the factor and technical strategy, the system also provides five adjustable parameters, including two markets, three optimization windows, two capital allocation methods, ten groups and five shareholdings, to test the impact of the
performance when experiment adjust it allocation.
Experiment show that some financial factors are still have value of stock selection in today's U.S. stock, especially PS have best correlation and profitability. And also found
that technical strategies could generally reduces maximum drawdown, bring the lower investment risk for investors.
摘要.................................................................................................................................i
Abstract.........................................................................................................................ii
致謝辭........................................................................................................................... iii
圖目錄........................................................................................................................... vi
表目錄......................................................................................................................... viii
第一章、 緒論........................................................................................................1
1.1 研究背景................................................................................................1
1.2 研究動機................................................................................................2
1.3 研究目的................................................................................................2
第二章、 文獻探討................................................................................................4
2.1 量化交易................................................................................................4
2.1.1 最佳化............................................................................................4
2.1.2 移動窗格........................................................................................6
2.2 因子投資................................................................................................7
2.2.1 多因子模型相關理論 ...................................................................7
2.2.2 量化多因子模型 ...........................................................................8
2.3 系統交易的資金配置計算 .................................................................10
2.3.1 個股每日賺賠表 .........................................................................10
2.3.2 資金權重配置表 .........................................................................11
2.3.3 績效表..........................................................................................12
第三章、 系統設計與實作 .................................................................................13
3.1 系統架構與流程 .................................................................................13
3.1.1 系統架構......................................................................................13
3.1.2 系統流程......................................................................................14
3.2 窗格切割..............................................................................................17
3.3 因子選股..............................................................................................18
3.3.1 標的排序......................................................................................18
3.3.2 標的分群......................................................................................19
3.3.3 標的選擇......................................................................................19
3.4 參數最佳化與回測 .............................................................................20
3.4.1 技術策略......................................................................................20
3.4.2 參數最佳化 .................................................................................21
3.4.3 回測..............................................................................................22
3.5 績效計算與儲存 .................................................................................22
3.5.1 每日權益計算 .............................................................................22
3.5.2 權益正規化 .................................................................................23
v
第四章、 系統驗證與分析 .................................................................................24
4.1 實驗變數..............................................................................................24
4.1.1 資料來源......................................................................................24
4.1.2 市場..............................................................................................24
4.1.3 因子組合......................................................................................24
4.1.4 技術策略......................................................................................27
4.1.5 窗格最佳化 .................................................................................27
4.1.6 資金配置法 .................................................................................27
4.1.7 群組..............................................................................................27
4.1.8 持有股數......................................................................................27
4.2 實驗設計..............................................................................................28
4.2.1 實驗流程......................................................................................28
4.2.2 實驗環境......................................................................................31
4.3 實驗結果..............................................................................................31
4.3.1 因子相關性及獲利性分析 .........................................................31
4.3.2 技術面策略有效性分析 .............................................................48
4.3.3 最佳化窗格績效分析 .................................................................55
4.3.4 資金配置之績效差異分析 .........................................................57
4.4 實驗系統效益 .....................................................................................62
第五章、 結論......................................................................................................63
5.1 結論......................................................................................................63
5.2 研究限制..............................................................................................64
5.3 未來建議..............................................................................................65
參考文獻......................................................................................................................66
附錄..............................................................................................................................68
Bollinger, J. (2001). Bollinger on Bollinger Bands. McGraw-Hill Education.
Carhart, M. M. (1997). On Persistence in Mutual Fund Performance. The Journal of
Finance, 52(1), 57-82.
Chan, E. P. (2008). Quantitative Trading: How to Build Your Own Algorithmic Trading
Business. Wiley.
Cohen, J. (1988). Statistical Power Analysis for the Behavioral Sciences (2th ed.).
Lawrence Erlbaum Associates.
Davey, K. J. (2014). Building Winning Algorithmic Trading Systems: A Trader's
Journey From Data Mining to Monte Carlo Simulation to Live Trading. Wiley.
Faith, C. (2007). Way of the Turtle: The Secret Methods That Turned Ordinary People
Into Legendary Traders. McGraw-Hill.
Fama, E. F., & French, K.R. (1993). Common risk factors in the returns on stocks and
bonds. Journal of Financial Economics, 33(1), 3-56.
Fama, E. F., & French, K.R. (2015). A five-factor asset pricing model. Journal of
Financial Economics, 116(1), 1-22.
Ger, S., Salehipour, A., Sim, A., & Wu, J. (2015). Backtest Overfitting: An Interactive
Example. Retrieved from University of California, Lawrence Berkeley National
Laboratory Web site: http://datagrid.lbl.gov/backtest/.
Graham, B., & Dodd, D. (1934). Security analysis: principles and technique. McGrawHill.
Pardo, R. (2008). The Evaluation and Optimization of Trading Strategies. Wiley.
Ross, S. A. (1976). The arbitrage theory of capital asset pricing. Journal of Economic
Theory, 13(3), 341-360.
Sharpe, W. F. (1964). Capital Asset Prices: A Theory of Market Equilibrium Under
67
Conditions of Risk. The Journal of Finance, 19(3), 425-442.
Tortoriello, R. (2008). Quantitative Strategies for Achieving Alpha: The Standard and
Poor's Approach to Testing Your Investment Choices. McGraw Hill Professional.
Wilder, J. W. (1978). New Concepts in Technical Trading Systems. Trend Research
丁鵬(2012)。量化投資:策略與技術。電子工業出版社。
石川(2020)。因子投資：方法與實踐。電子工業出版社。
卓育辰(2021)。結合因子分析與程式交易應用於台股之自動化回測與驗證平台。
國立中央大學資訊管理學系碩士論文，桃園市。
張林忠(2014)。分析師關鍵報告 2：張林忠教你程式交易。寰宇。
張維真（2019）。運用等分法與核心交易策略建構投資組合之自動化交易分析平
台—以美股為範例。國立中央大學資訊管理學系碩士論文，桃園市。
彭康哲（2016）。結合程式交易與選股模型的分析平台之設計與實作 – 以美國
股票市場為例。國立中央大學資訊管理學系碩士論文，桃園市。
廖顥軒(2022)。多樣性系統交易策略之績效比較與視覺化平台的設計與建置。國
立中央大學資訊管理學系碩士論文，桃園市。
蔡嘉民(2019)。程式交易的理論與實踐。經濟日報出版社。
穆慧萍(2008)。統計學。立信會計出版社。
Natenberg, S. (2014)。期權波動率與定價：高級交易測策略與技巧[韓冰潔，譯]。
機械工業出版社。(原著出版年：2014)