本研究將金融科技應用在資產管理領域為出發點，以台灣股票市場之上市櫃公司為例，將公司財報、個股動能、產業相關之公司特徵帶入機器學習eXtreme Gradient Boosting(XGBoost)模型分別進行以月頻、季頻的資產定價模型訓練。結果顯示，以季頻訓練之模型有較好的預測能力，並且在2016至2020年之回測期間，發現回測期間之重要特徵皆與產業相關。本研究將模型最佳之預測結果形成5, 10, 20, 30, 50檔標的之投資組合交易策略，在全公司樣本下，皆能在回測期間擊敗比較基準元大台灣50(0050)，其中最佳年化報酬可達到24.07%；更進一步將樣本區分為CSR公司，發現CSR公司之投資組合接能夠擊敗元大台灣50(0050)，雖然報酬明顯低於全公司樣本，不過風險也隨之下降，在最佳五檔投資組合中，可以獲得年化報酬率21.99%、夏普比率0.94之績效表現。

This research takes the application of financial technology in the field of asset management as the starting point. Taking the company’s financial reports, individual stock momentum, and industry-related company characteristics in the Taiwan stock market are incorporated into the machine learning eXtreme Gradient Boosting (XGBoost) model to train monthly and quarterly frequency asset pricing model, respectively.The results show that the model trained with quarterly frequency has better predictive ability, and during the back-test period from 2016 to 2020, it is found that the important features during the back-test period are all related to the industry. In this research, the best prediction results of the model were formed into 5, 10, 20, 30 and 50 target investment portfolio trading strategies. In the all-company sample, all of portfolio can beat the benchmark 0050 during the back-test period, and the best annualized return can reach 24.07%; The sample is further divided into CSR companies, and it is found that the investment portfolio of CSR companies can beat 0050. Although the return is significantly lower than the all-company sample, the risk also decreases. In the best top 5 investment portfolio, the annualized return rate is 21.99% and the Sharpe ratio is 0.94.

論文審定書 i
摘要 ii
Abstract iii
圖次 v
表次 vi
第壹章 緒論 1
第一節 研究背景與動機 1
第二節 研究目的 2
第三節 研究流程 2
第貳章 文獻探討 4
第一節 資產定價文獻 4
第二節 機器學習財務預測應用文獻 5
第三節 社會企業責任對於報酬影響的相關文獻 6
第四節 小結 7
第參章 研究方法 8
第一節 實驗架構 8
第二節 資料搜集與特徵建構 11
第三節 模型架構 22
第四節 交易策略 24
第肆章 實驗結果 25
第一節 模型有效性分析 25
第二節 模型回測與績效表現 28
第伍章 結論與後續建議 35
第一節 結論 35
第二節 後續建議 35
參考文獻 37

Ang, A., Hodrick, R. J., Xing, Y., & Zhang, X. (2006). The cross‐section of volatility and expected returns. The Journal of Finance, 61(1), 259-299.
Bali, T. G., Cakici, N., & Whitelaw, R. F. (2011). Maxing out: Stocks as lotteries and the cross-section of expected returns. Journal of Financial Economics, 99(2), 427-446.
Bhattacharyya, A., & Rahman, M. L. (2020). Mandatory CSR expenditure and stock return. Meditari Accountancy Research.
Carhart, M. M. (1997). On persistence in mutual fund performance. The Journal of Finance, 52(1), 57-82.
Dam, L. (2008) Corporate Social Responsibility and Financial Markets, PhD dissertation University of Groningen.
Dewi, D. M. (2013). CSR effect on market and financial performance. El Dinar, 1(02).
Green, J., Hand, J. R., & Zhang, X. F. (2017). The characteristics that provide independent information about average US monthly stock returns. The Review of Financial Studies, 30(12), 4389-4436.
Gu, S., Kelly, B., & Xiu, D. (2020). Empirical asset pricing via machine learning. The Review of Financial Studies, 33(5), 2223-2273.
Huang, A. G. (2009). The cross section of cashflow volatility and expected stock returns. Journal of Empirical Finance, 16(3), 409-429.
Jidong, L., & Ran, Z. (2018). Dynamic weighting multi factor stock selection strategy based on XGboost machine learning algorithm. Paper presented at the 2018 IEEE International Conference of Safety Produce Informatization (IICSPI).
Kim, Y., Li, H., & Li, S. (2014). Corporate social responsibility and stock price crash risk. Journal of Banking & Finance, 43, 1-13.
Liu, W. (2006). A liquidity-augmented capital asset pricing model. Journal of Financial Economics, 82(3), 631-671.
Margolis, J. D. & Walsh, J. P. (2001). People and profits? The search for a link between a company’s social and financial performance. Greenwich, CT: Erlbaum.
Orlitzky, M., Schmidt, F. L., & Rynes, S. L. (2003). Corporate social and financial performance: A meta-analysis. Organization Studies, 24(3), 403-441.
Raza, A., Ilyas, M. I., Rauf, R., & Qamar, R. (2012). Relationship between corporate social responsibility (CSR) and corporate financial performance (CFP): Literature review approach. Elixir Financial Management, 46(9), 8404-8409.
Sharpe, W. F. (1964). Capital asset prices: A theory of market equilibrium under conditions of risk. The Journal of Finance, 19(3), 425-442.
Tan, Z., Yan, Z., & Zhu, G. (2019). Stock selection with random forest: An exploitation of excess return in the Chinese stock market. Heliyon, 5(8), e02310.
Valta, P. (2016). Strategic default, debt structure, and stock returns. Journal of Financial and Quantitative Analysis, 51(1), 197-229.
Wu, C.-M., & Hu, J.-L. (2019). Can CSR reduce stock price crash risk? Evidence from China's energy industry. Energy Policy, 128, 505-518.
Zhong, X., & Enke, D. (2019). Predicting the daily return direction of the stock market using hybrid machine learning algorithms. Financial Innovation, 5(1), 1-20.