本研究利用 1997 至 2018 年台灣上市公司的資料，驗證了由 Blitz 和 Vliet
(2018)所提出的保守型投資公式應用在台灣市場的可能，利用簡單的三個因子，
低波動、高股利和正動量來形成投資組合。接著利用 Chen 和 Guestrin (2016)所
提出的機器學習演算法(XGBoost Model)，並在使用上述的三個因子，但考慮不
同周期的計算下，針對股票報酬建立報酬模型。為了檢驗模型成效，我們利用原
始的保守型投資組合作為基準，並依照模型產出的預測報酬對股票權重進行調整，
套用模型後我們不僅提高了 3%的 CAGR 更同時降低了 1%波動度。最後，我們
結合保守型公式，機器學習所建立的報酬模型和 Ghayur, Heaney 和 Platt (2018)所
提出的因子權重配置方式，建立出增值指數投組，並在最後獲得了 0.71 的資訊
比率。

This study uses the data of Taiwan-listed companies from 1997 to 2018 and
applying the conservative investment formula proposed by Blitz and Vliet (2018) in the
Taiwan market, using three simple factors, low volatility, high dividends and positive
momentum to form a portfolio. Then use the machine learning algorithm (XGBoost
Model) proposed by Chen and Guestrin (2016), and use the above three factors, but
consider the different calculation periods to build a return model. In order to test the
effectiveness of the model, we use the original conservative portfolio as the benchmark
and adjust the stock weight according to the predicted returns of the model. After
applying the model, we not only increase the CAGR by 3% but also reduce the volatility
by 1%. Finally, we combine the conservative formula, the return model based on
machine learning and the factor weighting approach proposed by Ghayur, Heaney and
Platt (2018) to construct a value-added index portfolio, and finally obtain an
information ratio of 0.71.

論文審定書 .................................................................................................................... i
摘要................................................................................................................................ ii
ABSTRACT ................................................................................................................ iii
I. Introduction .......................................................................................................... 1
1.1 Background Information ......................................................................... 1
1.2 Research Objective .................................................................................. 3
1.3 Research Framework ............................................................................... 4
II. Literature Review ................................................................................................ 6
2.1 Modern Portfolio Theory ........................................................................ 6
2.2 Machine Learning .................................................................................... 7
2.3 Portfolio Blending Approach ................................................................ 10
III. Data and Methodology ...................................................................................... 13
3.1 Analytical Procedures ............................................................................ 13
3.2 Data Description..................................................................................... 14
3.3 Conservative Formula ........................................................................... 16
3.4 Cross-sectional Return Model (Based on the XGBoost Model) ......... 19
3.5 Factor-combination Approaches .......................................................... 24
3.6 Performance Analysis ............................................................................ 27
IV. Empirical Analysis ............................................................................................. 30
4.1 Conservative Formula .............................................................................. 30
4.2 Cross-sectional Return Model (Based on the XGBoost Model) ............ 37
4.3 Enhanced Index Fund Construction ......................................................... 45
V. Conclusion .......................................................................................................... 48
5.1 Conclusion ............................................................................................... 48
5.2 Suggestion ................................................................................................ 49
VI. References ........................................................................................................... 52

1. Basu, S. (1977). Investment Performance of Common Stocks in Relation to Their
Price-Earnings Ratios: A Test of the Efficient Market Hypothesis. The Journal of
Finance, 32(3), 663-682.
2. Basu, S. (1983). The Relationship between Earnings Yield, Market Value and
Return for NYSE Common Stocks. Journal of Financial Economics, 12(1), 129
156.
3. Benartzi, S., & Thaler, R. (1993). Myopic Loss Aversion and the Equity Premium
Puzzle.
4. Bender, J., & Wang, T. (2015). Tilted and Anti-Tilted Portfolios: A Coherent
Framework for Advanced Beta Portfolio Construction. SSRN Electronic Journal.
5. Blitz, D V., & Vliet, P. (2018). The Conservative Formula: Quantitative Investing
Made Easy. The Journal of Portfolio Management, 44(7), 24-38.
6. Brown, D. P., & Rowe, B. (2007). The Productivity Premium in Equity Returns.
SSRN Electronic Journal.
7. Chen, T., & Guestrin, C. (2016). XGBoost. Proceedings of the 22nd ACM
SIGKDD International Conference on Knowledge Discovery and Data Mining -
KDD 16.
8. Clarke, R., Silva, H. D., & Thorley, S. (2016). Fundamentals of Efficient Factor
Investing (corrected May 2017). Financial Analysts Journal,72(6), 9-26.
9. Emami, S. (2018). Predicting Trend of Stock Prices by Developing Data Mining
Techniques with the Aim of Gaining Profit. Journal Of Accounting & Marketing
7(4).
10. Fama, E. F., & French, K. R. (1992). The Cross-Section of Expected Stock Returns.
The Journal of Finance, 47(2), 427-465.
52
11. Fama, E. F., & French, K. R. (1996). Multifactor Explanations of Asset Pricing
Anomalies. The Journal of Finance, 51(1), 55-84.
12. Fama, E. F., & French, K. R. (2015). A Five-factor Asset Pricing Model. Journal
of Financial Economics, 116(1), 1-22.
13. Gettleman, E., & Marks, J. M. (2006). Acceleration Strategies. SSRN Electronic
Journal.
14. Ghayur, K., Heaney, R., & Platt, S. (2019). Constructing Long-Only Multi-Factor
Strategies: Portfolio Blending versus Signal Blending. The Journal of Portfolio
Management Quantitative Special Issue, 45(3), 87-100.
15. Harvey, Liu, and Zhu (2015)…and the Cross-Section of Expected Returns. The
Review of Financial Studies, 29(1), 5-68.
16. Hou, K., Xue, C., & Zhang, L. (2015). Digesting Anomalies: An Investment
Approach. Review Of Financial Studies, 28(3), 650-705.
17. Hou, Kewei and Xue, Chen and Zhang, Lu(2017) Replicating Anomalies. 28th
Annual Conference on Financial Economics and Accounting
18. Jegadeesh, N. (1990). Evidence of Predictable Behavior of Security Returns. The
Journal of Finance, 45(3), 881.
19. 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.
20. Leippold, M., & Rregg, R. (2017). The Mixed vs the Integrated Approach to Style
Investing: Much Ado About Nothing? European Financial Management, 24(5),
829-855.
21. Leippold, M., & Vasiljevic, N. (2017). Option-Implied Intra-Horizon Value-at
Risk. SSRN Electronic Journal.
22. Lintner, J. (1965). Security Prices, Risk, and Maximal Gains From
Diversification. The Journal of Finance,20(4), 587-615.
53
23. Markowitz, H. (1952). Portfolio Selection. The Journal of Finance, 7(1), 77-91.
24. Mossin, J. (1966). Equilibrium in a Capital Asset Market. Econometrica,34(4),
768-783.
25. Ross, S. A. (1976). The Arbitrage Theory of Capital Asset Pricing. Journal of
Economic Theory, 13(3), 341-360.
26. Sharpe, W. F. (1964). Capital Asset Prices: A Theory of Market Equilibrium under
Conditions of Risk. The Journal of Finance, 19(3), 425-442.
27. Sugitomo, S., & Shotaro, M. (2018). Fundamental Factor Models Using Machine
Learning. SSRN Electronic Journal.
28. Treynor, J. L. (1961). Market Value, Time, and Risk. SSRN Electronic Journal.