量化投資在近年來已經受專業投資人所青睞，同時機器學習在金融領域上的應用已經日漸頻繁，本研究將一般量化投資會使用到的資料結合機器學習模型，同時納入先前研究所認為可以有效解釋股市大跌的特徵，嘗試預測未來的負偏度(Negative Coefficient of Skewness)，以下稱NCSKEW和漲跌波動度(Down-to-UP volatility)，以下稱DUVOL，找出重要的特徵和將預測結果進行建模，建立最適合的投組。經研究結果後發現(一)在預測漲跌波動度上有比較好的準確度。(二)所建構出的特殊指標會比一般的財報、總經指標要來的重要，表示將指標進行處理後會更加的有用。(三)在投資組合的建構上，我們使用負偏度的預測結果透過流動性篩選之後建構的投組在長時間有最好的表現，可以超過台灣加權指數和0050的報酬。

Quantitative investment has been favored by professional investors in recent years, and the application of machine learning in the financial field has become more and more frequent. This study combines the quantitative investment and machine learning by using the features proved useful to explain the stock market crash. Also, I try to predict the NCSKEW and DUVOL in the future, and find out the important features, then model the prediction results, establishing the most suitable portfolio. Finally, I find that (1) the model has a relatively good accuracy in predicting the DUVOL. (2) The special indicators constructed will be more important than the general financial report and macroeconomic indicators, indicating that the indicators will be more useful after processing. (3) I use the NCSKEW prediction results to construct the investment group after the liquidity screening has the best performance in a long time, which can outperform the return of the TAIEX and 0050.

論文審定書 i
摘要 ii
Abstract iii
List of Figures vi
List of Tables vii
Chapter1 Introduction 1
1.1 Motivation 1
1.2 Purpose 2
1.3 Framework 3
Chapter2 Literature review 5
2.1 Machine Learning Applications in Finance 5
2.2 Feature Selection 6
2.3 Stock Price Crash Risk 10
Chapter3 Research Methodology 13
3.1 Process 13
3.2 Data 13
3.3 Features Construction 14
3.3.1 Features Introduction 14
3.3.2 Features Preprocessing and Generation 26
3.4 Model 27
3.4.1 Model Introduction 27
3.4.2 Model Construction 28
3.4.3 Model Measured Method 30
3.5 Portfolio Construction 31
3.6 Backtesting Performance 32
3.6.1 Portfolio Measured Method 33
Chapter4 Results 35
4.1 Prediction results 35
4.2 Feature Importance 38
4.3 Portfolio Performance 41
Chapter5 Conclusions 55
5.1 Results 55
5.2 Suggestions 55
References 57

1. Markowitz, H. (1952). Portfolio Selection. The Journal of Finance.
2. 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.
3. Fama, E. F., & French, K. R. (2015). A five-factor asset pricing model. Journal of Financial Economics, 116(1), 1-22.
4. Butaru, F., Chen, Q., Clark, B., Das, S., Lo, A. W., & Siddique, A. (2016). Risk and risk management in the credit card industry. Journal of Banking & Finance, 72, 218-239. https://doi.org/10.1016/j.jbankfin.2016.07.015
5. Emir, S., Dinçer, H., & Timor, M. (2012). A stock selection model based on fundamental and technical analysis variables by using artificial neural networks and support vector machines. Review of Economics & Finance, 2(3), 106-122.
6. Freyberger, J., Neuhierl, A., & Weber, M. (2020). Dissecting characteristics nonparametrically. The Review of Financial Studies, 33(5), 2326-2377.
7. Giglio, S., & Xiu, D. (2021). Asset pricing with omitted factors. Journal of Political Economy, 129(7), 1947-1990.
8. Heaton, J. B., Polson, N. G., & Witte, J. H. (2017). Deep learning for finance: deep portfolios. Applied Stochastic Models in Business and Industry, 33(1), 3-12.
9. Hutchinson, J. M., Lo, A. W., & Poggio, T. (1994). A Nonparametric Approach to Pricing and Hedging Derivative Securities Via Learning Networks. The Journal of Finance, 49(3). https://doi.org/10.1111/j.1540-6261.1994.tb00081.x
10. Kelly, B. T., Pruitt, S., & Su, Y. (2019). Characteristics are covariances: A unified model of risk and return. Journal of Financial Economics, 134(3), 501-524. https://doi.org/10.1016/j.jfineco.2019.05.001
11. Khandani, A. E., Kim, A. J., & Lo, A. W. (2010). Consumer credit-risk models via machine-learning algorithms. Journal of Banking & Finance, 34(11), 2767-2787. https://doi.org/10.1016/j.jbankfin.2010.06.001
12. Kim, J.-B., Li, L., Lu, L. Y., & Yu, Y. (2016). Financial statement comparability and expected crash risk. Journal of Accounting and Economics, 61(2-3), 294-312. https://doi.org/10.1016/j.jacceco.2015.12.003
13. Kothari, S. P., Shu, S., & Wysocki, P. D. (2009). Do managers withhold bad news? Journal of Accounting research, 47(1), 241-276.
14. Kozak, S., Nagel, S., & Santosh, S. (2020). Shrinking the cross-section. Journal of Financial Economics, 135(2), 271-292. https://doi.org/10.1016/j.jfineco.2019.06.008
15. Moritz, B., & Zimmermann, T. (2016). Tree-based conditional portfolio sorts: The relation between past and future stock returns. Available at SSRN 2740751.
16. Rapach, D. E., Strauss, J. K., & Zhou, G. (2013). International Stock Return Predictability: What Is the Role of the United States? The Journal of Finance, 68(4), 1633-1662. https://doi.org/10.1111/jofi.12041
17. Tsai, C.-F., & Hsiao, Y.-C. (2010). Combining multiple feature selection methods for stock prediction: Union, intersection, and multi-intersection approaches. Decision Support Systems, 50(1), 258-269. https://doi.org/10.1016/j.dss.2010.08.028
18. Xiu, D., Kelly, B., Gu, S., & Karolyi, A. (2020). Empirical Asset Pricing via Machine Learning. The Review of Financial Studies, 33(5), 2223-2273. https://doi.org/10.1093/rfs/hhaa009
19. Yao, J., Li, Y., & Tan, C. L. (2000). Option price forecasting using neural networks. Omega, 28(4), 455-466.
20. Zou, L., Tang, T., & Li, X. (2016). The stock preferences of domestic versus foreign investors: Evidence from Qualified Foreign Institutional Investors (QFIIs) in China. Journal of Multinational Financial Management, 37, 12-28.
21. Zouaoui, M., Nouyrigat, G., & Beer, F. (2011). How does investor sentiment affect stock market crises? Evidence from panel data. Financial Review, 46(4), 723-747.
22. Habib, A., Hasan, M. M., & Jiang, H. (2018). Stock price crash risk: review of the empirical literature. Accounting & Finance, 58, 211-251. https://doi.org/10.1111/acfi.12278
23. Chen, C., Kim, J.-B., & Yao, L. (2017). Earnings smoothing: Does it exacerbate or constrain stock price crash risk? Journal of Corporate Finance, 42, 36-54. https://doi.org/10.1016/j.jcorpfin.2016.11.004
24. Kim, J.-B., Li, Y., & Zhang, L. (2011). Corporate tax avoidance and stock price crash risk: Firm-level analysis. Journal of Financial Economics, 100(3), 639-662. https://doi.org/10.1016/j.jfineco.2010.07.007
25. Kim, J.-B., & Zhang, L. (2016). Accounting Conservatism and Stock Price Crash Risk: Firm-level Evidence. Contemporary Accounting Research, 33(1), 412-441. https://doi.org/10.1111/1911-3846.12112
26. Andreou, P. C., Louca, C., & Petrou, A. P. (2017). CEO Age and Stock Price Crash Risk*. Review of Finance, 21(3), 1287-1325. https://doi.org/10.1093/rof/rfw056
27. Chen, J., Hong, H., & Stein, J. C. (2001). Forecasting crashes: Trading volume, past returns, and conditional skewness in stock prices. Journal of Financial Economics, 61(3), 345-381.
28. Chang, X., Chen, Y., & Zolotoy, L. (2017). Stock liquidity and stock price crash risk. Journal of financial and quantitative analysis, 52(4), 1605-1637.
29. Andreou, P. C., Antoniou, C., Horton, J., & Louca, C. (2016). Corporate Governance and Firm-specific Stock Price Crashes. European Financial Management, 22(5), 916-956. https://doi.org/10.1111/eufm.12084
30. Velury, U., & Jenkins, D. S. (2006). Institutional ownership and the quality of earnings. Journal of business research, 59(9), 1043-1051.
31. Luo, J.-h., Gong, M., Lin, Y., & Fang, Q. (2016). Political connections and stock price crash risk: evidence from China. Economics Letters, 147, 90-92.
32. Lee, W., & Wang, L. (2017). Do political connections affect stock price crash risk? Firm-level evidence from China. Review of Quantitative Finance and Accounting, 48(3), 643-676.