本研究以拔靴法評估資料挖掘於基本面分析下異常報酬現象之影響。研究發現基本面之異常報酬並非抽樣變異所造成，且眾多基本面因子確實存在橫斷面股價報酬之預測能力。另外，研究發現基本面分析影響力最高之變數大多數為融資現金流與盈餘相關之會計變數。本研究亦發現基本面變數可強化ESG (environmental, social and corporate governance)公司之投資組合報酬率。進一步，本文使用機器學習演算法中之支援向量機搭配基本面之變數以建立選股模型強化基本面變數所建構之投資組合。實證結果顯示使用基本面變數下之選股模型所建構之投資組合，其績效優於大盤報酬率。另一方面，本研究亦基於原始基本面投資組合搭配機器學習之選股模型所形成之新投資組合，其績效亦優於以原始基本面所建構之投資組合。

In this paper, we use a bootstrap method to estimate the effect of data-mining on fundamental-based anomalies. We find that fundamental-based anomalies are not due to sampling variation and a lot of fundamental signals are actually powerful predictors of cross-sectional stock returns. Furthermore, most of these top fundamental signals are related to cash flow in finance and earning distribution. Our findings indicate that this predictive ability of fundamental signals also exists in the sample of ESG (environmental, social and corporate governance) companies. Then, we also use fundamental signals as predictors and popular classifier (e.g. SVM) to build a stock selection model. Therefore, the empirical results show that the portfolios of stock selection model using fundamental predictors can beat the benchmark. On the other hand, the new portfolios based on the original long-short portfolios and stock selection model can earn more excess returns than the original fundamental-based portfolios.

論文審定書 i
摘要 ii
ABSTRACT iii
CONTENT iv
LIST OF FIGURES v
LIST OF TABLES vii
1. INTRODUCTION 1
1.1 Background 1
1.2 Purpose 2
2. LITERATURE REVIEWS 4
2.1 Traditional asset pricing theory 4
2.2 Machine learning 5
3. DATA AND METHODOLOGY 9
3.1 Data and financial signals 9
3.2 Long-short fundamental-based portfolios 11
3.3 The bootstrap approach 12
3.4 The ESG sample 15
3.5 Stock selection using SVM 16
3.6 Class imbalance 20
3.7 Portfolio based on financial signals and selection model 24
4. EMPIRICAL RESULTS 26
4.1 Results for the bootstrap approach 26
4.2 Cross-sectional anomalies based on the top fundamental signals 30
4.3 Robust tests 33
4.4 Strengthening for ESG stocks 35
4.5 Stock selection model 38
5. CONCLUSION 42
REFERENCES 45
Appendix A: List of accounting variables 63
Appendix B: List of financial ratios and configurations 65

中文部分
1. 林宗勳(2006)，Support Vector Machines 簡介，台灣大學通訊與多媒體實驗室。
外文部分
1. Ban, G. Y., El Karoui, N., & Lim, A. E. (2016). Machine learning and portfolio optimization. Management Science, 64(3), 1136-1154.
2. Bradshaw, M. T., Richardson, S. A., & Sloan, R. G. (2006). The relation between corporate financing activities, analysts’ forecasts and stock returns. Journal of Accounting and Economics, 42(1-2), 53-85.
3. Carhart, M. M. (1997). On persistence in mutual fund performance. The Journal of Finance, 52(1), 57-82.
4. Chan, K., Chan, L. K., Jegadeesh, N., & Lakonishok, J. (2006). Earnings Quality and Stock Returns. The Journal of Business, 79(3), 1041-1082.
5. Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321-357.
6. Cochrane, J. H. (2011). Presidential address: Discount rates. The Journal of Finance, 66(4), 1047-1108.
7. Cooper, M. J., Gulen, H., & Schill, M. J. (2008). Asset growth and the cross‐section of stock returns. The Journal of Finance, 63(4), 1609-1651.
8. Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273-297.
9. 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.
10. Fama, E. F., & French, K. R. (1996). Multifactor explanations of asset pricing anomalies. The Journal of Finance, 51(1), 55-84.
11. Fama, E. F., & French, K. R. (2008). Dissecting anomalies. The Journal of Finance, 63(4), 1653-1678.
12. Fama, E. F., & French, K. R. (2010). Luck versus skill in the cross‐section of mutual fund returns. The Journal of Finance, 65(5), 1915-1947.
13. Fama, E. F., & French, K. R. (2015). A five-factor asset pricing model. Journal of Financial Economics, 116(1), 1-22.
14. Fama, E. F., & French, K. R. (2016). Dissecting anomalies with a five-factor model. The Review of Financial Studies, 29(1), 69-103.
15. Fan, A., & Palaniswami, M. (2001). Stock selection using support vector machines. In IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Vol. 3, pp. 1793-1798).
16. Foster, F. D., Smith, T., & Whaley, R. E. (1997). Assessing goodness‐of‐fit of asset pricing models: The distribution of the maximal R 2. The Journal of Finance, 52(2), 591-607.
17. Freyberger, J., Neuhierl, A., & Weber, M. (2017). Dissecting Characteristics Nonparametrically (No. w23227). National Bureau of Economic Research.
18. Green, J., Hand, J. R., & Zhang, X. F. (2013). The supraview of return predictive signals. Review of Accounting Studies, 18(3), 692-730.
19. Green, J., Hand, J. R., & Zhang, X. F. (2014). The remarkable multidimensionality in the cross-section of expected US stock returns. Available at SSRN, 2262374.
20. Han, H., Wang, W. Y., & Mao, B. H. (2005, August). Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning. In International Conference on Intelligent Computing (pp. 878-887). Springer, Berlin, Heidelberg.
21. Harvey, C. R., Liu, Y., & Zhu, H. (2016). … and the cross-section of expected returns. The Review of Financial Studies, 29(1), 5-68.
22. He, H., Bai, Y., Garcia, E. A., & Li, S. (2008, June). ADASYN: Adaptive synthetic sampling approach for imbalanced learning. In 2008 IEEE International Joint Conference on Neural Networks (pp. 1322-1328).
23. Heston, S. L., & Sinha, N. R. (2017). News vs. sentiment: Predicting stock returns from news stories. Financial Analysts Journal, 73(3), 67-83.
24. Horowitz, J. L. (2001). The bootstrap. In Handbook of econometrics (Vol. 5, pp. 3159-3228). Elsevier.
25. Hou, K., Xue, C., & Zhang, L. (2015). Digesting anomalies: An investment approach. The Review of Financial Studies, 28(3), 650-705.
26. Karolyi, G. A., & Kho, B. C. (2004). Momentum strategies: Some bootstrap tests. Journal of Empirical Finance, 11(4), 509-536.
27. Kosowski, R., Naik, N. Y., & Teo, M. (2007). Do hedge funds deliver alpha? A Bayesian and bootstrap analysis. Journal of Financial Economics, 84(1), 229-264.
28. Kosowski, R., Timmermann, A., Wermers, R., & White, H. (2006). Can mutual fund “stars” really pick stocks? New evidence from a bootstrap analysis. The Journal of Finance, 61(6), 2551-2595.
29. Lev, B., & Thiagarajan, S. R. (1993). Fundamental information analysis. Journal of Accounting research, 31(2), 190-215.
30. Li, F. (2010). The information content of forward‐looking statements in corporate filings—A naïve Bayesian machine learning approach. Journal of Accounting Research, 48(5), 1049-1102.
31. Lo, A. W., & MacKinlay, A. C. (1990). Data-snooping biases in tests of financial asset pricing models. The Review of Financial Studies, 3(3), 431-467.
32. Luss, R., & d’Aspremont, A. (2015). Predicting abnormal returns from news using text classification. Quantitative Finance, 15(6), 999-1012.
33. McLean, R. D., & Pontiff, J. (2016). Does academic research destroy stock return predictability?. The Journal of Finance, 71(1), 5-32.
34. Merton, R. (1987). On the state of the efficient market hypothesis in financial economics. Macroeconomics and Finance: Essays in Honor of Franco Modigliani, 93-124.
35. Moritz, B., & Zimmermann, T. (2016). Tree-based conditional portfolio sorts: The relation between past and future stock returns. Available at SSRN 2740751.
36. Mullainathan, S., & Spiess, J. (2017). Machine learning: an applied econometric approach. Journal of Economic Perspectives, 31(2), 87-106.
37. Ou, J. A., & Penman, S. H. (1989). Financial statement analysis and the prediction of stock returns. Journal of accounting and economics, 11(4), 295-329.
38. Piotroski, J. D. (2000). Value investing: The use of historical financial statement information to separate winners from losers. Journal of Accounting Research, 38, 1-52.
39. Renault, T. (2017). Intraday online investor sentiment and return patterns in the US stock market. Journal of Banking & Finance, 84, 25-40.
40. Sullivan, R., Timmermann, A., & White, H. (1999). Data‐snooping, technical trading rule performance, and the bootstrap. The Journal of Finance, 54(5), 1647-1691.
41. Sullivan, R., Timmermann, A., & White, H. (2001). Dangers of data mining: The case of calendar effects in stock returns. Journal of Econometrics, 105(1), 249-286.
42. Thomas, J. K., & Zhang, H. (2002). Inventory changes and future returns. Review of Accounting Studies, 7(2-3), 163-187.
43. Vapnik, V. (1995). The Nature of Statistical Learning Theory. Springer-Verlag, New York, Inc.
44. Yan, X., & Zheng, L. (2017). Fundamental analysis and the cross-section of stock returns: A data-mining approach. The Review of Financial Studies, 30(4), 1382-1423.