本研究主要探討總體經濟變數是否能對美國S&P500指數的熊市做預測，本文考慮的總體經濟變數有長短期利差、通貨膨脹率、M1成長率、M2成長率、工業生產成長率、失業率變動、聯邦資金利率變動、消費者物價指數成長等等。在過去歷史文獻中，熊市預測的研究方法多以probit模型去對各種總體經濟變數檢測是否具有預測力，最近幾年，機器學習以及深度學習不管在學術界還是在業界都被廣泛的應用，是非常熱門的領域之一。因此本研究嘗試用XGBoost(eXtreme Gradient Boosting)以及LSTM(Long short-term memory)作為研究工具，先將S&P500的月報酬資料用非參數法的Bry-Boschan法去認定熊市，再透過XGBoost以及LSTM模型去分析總體經濟變數對於牛熊市的預測表現，最後再將這兩種方法的預測結果去做比較，預測結果顯示，LSTM模型的預測表現優於XGBoost模型，準確率為84%，且長短期利差為本研究選取的總體變數中，特徵重要度最高的，特徵重要度最低的則為失業率。

This paper mainly investigates whether the macroeconomic variables can predict the bear market of the US S&P 500 index. The macroeconomic variables considered in this article include interest rate spreads, inflation rates, M1 growth rate, M2 growth rate, industrial production growth rate, unemployment rates, federal funds rates, federal government debt, and nominal exchange rates. In the past historical literature, the research methods of recessions in the stock market prediction mainly use the probit model to evaluate whether there is a predictive power for various macroeconomic variables. Therefore, this study attempts to use XGBoost model and LSTM model . First, we use Bry-Boschan approach of the monthly return data of S&P 500 to identify recession periods in the stock market, and then we use XGBoost model and LSTM model to predict both in-sample and out-of-sample tests of the variable’s predictive ability. The results of the research show that the performance of LSTM model is the better than XGBoost model.The accuaracy of LSTM model is 84%. The interest rate spreads is the highest feature importance,and the unemployment rates is the lowest feature importance.

1、緒論 5
2、牛熊市的定義 8
3、研究方法 9
3.1、XGBoost模型 9
3.1.1、XGBoost實現原理 9
3.1.2、XGBoost模型定義 10
3.2、LSTM模型 12
4、資料來源及變數分析 17
5、研究結果 21
5.1、模型評估 21
5.2、模型預測結果 25
6、結論 30

1.Abdullah, D. A., & Hayworth, S. C. (1993). Macroeconometrics of stock price fluctuations. Quarterly Journal of Business and Economics, 50-67.

2.Asprem, M. (1989). Stock prices, asset portfolios and macroeconomic variables in ten European countries. Journal of Banking & Finance, 13(4-5), 589-612.

3.Bhaduri, S., & Saraogi, R. (2010). The predictive power of the yield spread in timing the stock market. Emerging Markets Review, 11(3), 261-272.

4.Bohl, M. T., Siklos, P. L., & Werner, T. (2007). Do central banks react to the stock market? The case of the Bundesbank. Journal of Banking & Finance, 31(3), 719-733.

5.Candelon, B., Piplack, J., & Straetmans, S. (2008). On measuring synchronization of bulls and bears: The case of East Asia. Journal of Banking & Finance, 32(6), 1022-1035.

6.Chen, S.-S. (2009). Predicting the bear stock market: Macroeconomic variables as leading indicators. Journal of Banking & Finance, 33(2), 211-223.

7.Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boostingsystem. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794).

8.Frauendorfer, K., Jacoby, U., & Schwendener, A. (2007). Regime switching based portfolio selection for pension funds. Journal of Banking & Finance, 31(8), 2265-2280.

9.Guresen, E., Kayakutlu, G., & Daim, T. U. (2011). Using artificial neural network models in stock market index prediction. Expert Systems with Applications, 38(8), 10389-10397.

10.Hamburger, M. J., & Kochin, L. A. (1972). Money and stock prices: The channels of influences. The journal of Finance, 27(2), 231-249.

11.Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.

12.Keim, D. B., & Stambaugh, R. F. (1986). Predicting returns in the stock and bond markets. Journal of financial Economics, 17(2), 357-390.

13.Kimoto, T., Asakawa, K., Yoda, M., & Takeoka, M. (1990). Stock market prediction system with modular neural networks. Paper presented at the 1990 IJCNN international joint conference on neural networks.

14.Lewellen, J. (2004). Predicting returns with financial ratios. Journal of financial Economics, 74(2), 209-235.

15.Maheu, J. M., & McCurdy, T. H. (2000). Identifying bull and bear markets in stock returns. Journal of Business & Economic Statistics, 18(1), 100-112.

16.Pagan, A. R., & Sossounov, K. A. (2003). A simple framework for analysing bull and bear markets. Journal of applied econometrics, 18(1), 23-46.

17.Pearce, D. K., & Roley, V. V. (1984). Stock prices and economic news (No. w1296). National bureau of economic research.

18.Pontiff, J., & Schall, L. D. (1998). Book-to-market ratios as predictors of market returns. Journal of financial Economics, 49(2), 141-160.

19.Rapach, D. E., Wohar, M. E., & Rangvid, J. (2005). Macro variables and international stock return predictability. International journal of forecasting, 21(1), 137-166.

20.Sill, D. K. (1993). Predicting stock-market volatility. Business Review, (Jan), 15-28.

21.Sugitomo, S., & Shotaro, M. (2018). Fundamental Factor Models Using Machine Learning. Available at SSRN 3322187.

22.Thorbecke, W. (1997). On stock market returns and monetary policy. The journal of Finance, 52(2), 635-654.