在投資領域文獻使用決策樹中的 Classification And Regression Tree 模型去做 股票的挑選進而建構投資組合，而這些文獻都是建構在國外的市場上，本研究目 的為檢驗台灣市場是否適用此因子擇時模型建構增值型指數基金。
本研究使用 Miller et al (2015)的方法，利用資訊係數(Information Coefficient) 當作判斷因子效果的依據，使用決策樹中的 CART 利用預測變數建立因子擇時模 型個別預測動能、價值與波動度因子的有效性，將有效的因子利用 z 分數組成複 合因子，排序選出表現較好與表現較差股票作加減碼，建構一個增值型指數基 金。
實證結果顯示，由於因子的效果是持續一段時間的，故在本論文建構因子擇 時模型時去比較累積資訊係數與一期資訊係數相比，在樣本內期間訓練的擇時模 型累積資訊係數較好，多空策略的績效顯示有因子擇時的多空策略是較好的，在 台灣市場上使用因子擇時模型是較佳的，建構增值型指數基金有好的績效，其資 訊比例(Information Ratio)高達 0.95。

There is much literature in the field of investment using the Classification and Regression Trees (CART) model to select stocks and construct a portfolio built on a foreign market. The purpose of this study is to examine whether the factor timing model is applicable to construct enhanced index funds in the Taiwan market.
In this study, we use the method proposed by Miller et al. (2015), which uses the information coefficient as an indicator for judging the effectiveness of factors. Using the CART to establish a factor timing model to forecast effective factors, the effective factors are formed into a composite factor using the z-score of effective factors. This research uses the composite factor to select outperformers and underperformers in the stock pool to construct an enhanced index fund.
The empirical results show that the use of this sample to compare the factor timing model indicates that the performance of a long-short strategy with factor timing is better than without factor timing in the Taiwan market, and when an enhanced index fund has a good performance, the information ratio of the enhanced index fund is 0.95.

論文審定書 i
誌謝 ii
摘要 iii
ABSTRACT iv
CONTENTS v
List of Figures vii
List of Tables viii
I. INTRODUCTION 1
1.1 Background Information 1
1.2 Research Purpose 3
1.3 Research Structure 3
II. LITERATURE REVIEW 5
2.1 Modern Portfolio Theory 5
2.2 Factor Analysis 5
2.3 Information Coefficient 6
2.4 Classification And Regression Trees 7
2.5 Risk-controlled Active 7
III. METHODOLOGY 9
3.1 Data Description 9
3.2 Information Coefficient 12
3.3 Factor Timing Model 13
3.4 Construction of Benchmark Index 14
3.5 Construction of Enhanced Index Fund 15
3.6 Turnover Rate 18
3.7 Performance Measure 19
IV. EMPIRICAL RESULTS 21
4.1 Data 21
4.2 Factor Timing Model 21
4.3 Comparison of the Model 26
4.4 Enhanced Index Fund 29
V. CONCLUSION 36
VI. REFERENCES 40
APPENDIX: Descriptor Definitions 43

Baker, N. L., & Haugen, R. A. (2012), “Low Risk Stocks Outperform within All Observable Markets of the World.” Working paper.
Breiman, L., Friedman, J., Stone, C. J., & Olshen, R. A. (1984), “Classification and Regression Trees.” CRC press.
Carhart, M. M. (1997), “On Persistence in Mutual Fund Performance.” Journal of Finance, 52(1), pp. 57-82.
Chow, T. M., Hsu, J. C., Kuo, L. L., & Li, F. (2014), “A Study of Low Volatility Portfolio Construction Methods.” Journal of Portfolio Management, 40(4), pp. 89-115.
Daniel, K., & Moskowitz, T. J. (2016), “Momentum Crashes.” Journal of Finance Economics, 122(2), pp.221-247.
Ghayur, K., Heaney, R., & Platt, S. (2013), “Low-volatility Investing: Balancing Total Risk and Active Risk Considerations.” Journal of Portfolio Management, 40(1), pp. 49-60.
Grinold, R.C. (1989), “The Fundamental Law of Active Management.” Journal of Portfolio Management, 15(3), pp. 30-37.
Hsu, Y. H., Jeng, Y., Tzang, S. W. and Lee Y. H. (2011), “Enhanced Index Fund Performance Analysis by Multi-Factor Alpha Model: Evidence from Taiwan.” 2011 International Conference of Taiwan Finance Association.
Jegadeesh, N., and Titman, S. (1993), “Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency.” Journal of Finance, 48(1), pp. 65-91.
Jeng, Y., Lee, C. J., & Tzang, S. W. (2013). “Application of a Multifactor Model in Enhanced Index Fund: Performance Analysis in China.” Emerging Markets Finance and Trade, 49(4), pp.163-183.
Miller, K. L., Li, H., Zhou, T. G., & Giamouridis, D. (2015), “A Risk-Oriented Model for Factor Timing Decisions.” Journal of Portfolio Management, 41(3), pp.46-58.
Qian, E. E., Hua, R. H., & Sorensen, E. H. (2007), “Quantitative Equity Portfolio Management: Modern Techniques and Applications.” CRC Press.
Riepe, M. W. and M. D. Werner. (1998), “Are Enhanced Index Mutual Funds Worthy of Their Name?” Journal of Investing, 18(3), pp. 6-15.
Sezgin, F. H. (2010), “An Empirical Investigation of the Relationship Among P/E Ratio, Stock Return and Dividend Yields for Istanbul Stock Exchange.” International Journal of Economics and Finance Studies, 2(1), pp. 16-23.
Sorensen, E. H., Miller, K. L., & Ooi, C. K. (2000), “The Decision Tree Approach to Stock Selection.” Journal of Portfolio Management, 27(1), pp. 42-52.
Zhu, M., Philpotts, D., Sparks, R., & J. Stevenson, M. (2011), “A Hybrid Approach to Combining CART and Logistic Regression for Stock Ranking.” Journal of Portfolio Management, 38(1), pp. 100-109.
Zhu, M., Philpotts, D., & Stevenson, M. J. (2012). “The Benefits of Tree-Based Models for Stock Selection.” Journal of Asset Management, 13(6), pp. 437-448.