本文的主要目的是以機器學習來驗證宏觀經濟數據、籌碼面數據和風險情緒指標對於外匯的樣本外預測能力，研究對象為歐元兌美元(EURUSD)，研究時間為2007年3月至2020年7月。觀察過去傳統外匯預測模型普遍的預測效果不佳，且近期許多文章透過機器學習和深度學習的方式大多是使用技術指標來預測外匯走勢，針對宏觀經濟數據的研究相對較少。本文除了使用傳統預測外匯模型之數據外，更考量製造業PMI、零售銷售數據、工業生產值等重要的經濟數據，同時引入籌碼面數據及市場風險情緒指標，嘗試驗證不同的變數和機器學習方法對於外匯變動的預測效果。再者，本研究與傳統論文的不同處在於資料前處理的部分，為了有效萃取出數據中的資訊，本文將經濟數據轉換為月/季/年增率，將兩國的數據作差值並標準化後作為模型的特徵。實證結果發現基本面數據確實被驗證出隱含能夠改善模型的資訊，且在長天期和金融危機時的效果更加顯著。相較於基準模型，加入基本面數據確實可以增加模型的訓練及預測效果。最後，本文發現不同的機器學習模型會有不同的適用時期，其中支援向量機模型(Support Vector Machine model, SVM)在各種的情況下均有可靠的驗證效果。

The main purpose of this paper is to examine the direction predictability of Euro-dollar using fundamental data, chip indicator and risk sentiment indicator during 2007 March to 2020 July. Several previous researches showed that traditional forex models generally have poor predictive power. Many recent articles using machine learning and deep learning methodology to predict currency exchange rate, but most of them use technical indicators, and relatively few studies focus on the effect of fundamental data. In this paper, we add manufacturing PMI, retail sales, and industrial production value to fundamental economic data. We also consider chip indicators and risk sentiment indicator to see whether they could bring incremental prediction power to different machine learning models. In addition, in order to effectively extract the information from the fundamental data, we convert the data into monthly/quarterly/yearly growth rate and to standardizes them. The empirical results show that the fundamental data do improve the validation power, especially more significant in the long term forecasting and in the period of financial crisis. Compared with the benchmark model, adding fundamental data can indeed increase the training and validation performance. Finally, we find that different machine learning models have their suitable periods, and Support Vector Machine model (SVM) are suitable in various situations.

[1] Amat, C., Michalski, T., & Stoltz, G. (2018). Fundamentals and exchange rate forecastability with simple machine learning methods. Journal of International Money and Finance, 88, 1-24.

[2] Cassel, G. (1916). The present situation of the foreign exchanges. The Economic Journal, 26(101), 62-65.

[3] Carapuço, J., Neves, R., & Horta, N. (2018). Reinforcement learning applied to Forex trading. Applied Soft Computing, 73, 783-794.

[4] Camacho, M., & Perez‐Quiros, G. (2010). Introducing the euro‐sting: Short‐term indicator of euro area growth. Journal of Applied Econometrics, 25(4), 663-694.

[5] Chen, Y. S., Cheng, C. H., & Tsai, W. L. (2014). Modeling fitting-function-based fuzzy time series patterns for evolving stock index forecasting. Applied intelligence, 41(2), 327-347.

[6] Cheung, Y. W., Chinn, M. D., Pascual, A. G., & Zhang, Y. (2019). Exchange rate prediction redux: New models, new data, new currencies. Journal of International Money and Finance, 95, 332-362.

[7] Dal Bianco, M., Camacho, M., & Quiros, G. P. (2012). Short-run forecasting of the euro-dollar exchange rate with economic fundamentals. Journal of International Money and Finance, 31(2), 377-396.

[8] Dash, R. (2020). Performance analysis of an evolutionary recurrent Legendre Polynomial Neural Network in application to FOREX prediction. Journal of King Saud University-Computer and Information Sciences, 32(9), 1000-1011.

[9] Eng, M. H., Li, Y., Wang, Q. G., & Lee, T. H. (2008, December). Forecast forex with ANN using fundamental data. In 2008 International Conference on Information Management, Innovation Management and Industrial Engineering (Vol. 1, pp. 279-282). IEEE.

[10] Evans, M. D., & Lyons, R. K. (2002). Order flow and exchange rate dynamics. Journal of political economy, 110(1), 170-180.

[11] Fakhr, M. W., & Baasher, A. (2011). Forex daily trend prediction using machine learning techniques. In ACS'11 Proceedings of the 11th WSEAS International Conference on Applied Computer Science (pp. 41-47).

[12] Froot, K. A., & Ramadorai, T. (2005). Currency returns, intrinsic value, and institutional‐investor flows. The Journal of Finance, 60(3), 1535-1566.

[13] Galeshchuk, S., & Mukherjee, S. (2017). Deep networks for predicting direction of change in foreign exchange rates. Intelligent Systems in Accounting, Finance and Management, 24(4), 100-110.

[14] Hajizadeh, E., Mahootchi, M., Esfahanipour, A., & Kh, M. M. (2019). A new NN-PSO hybrid model for forecasting Euro/Dollar exchange rate volatility. Neural Computing and Applications, 31(7), 2063-2071.

[15] Islam, M., Hossain, E., Rahman, A., Hossain, M. S., & Andersson, K. (2020). A review on recent advancements in forex currency prediction. Algorithms, 13(8), 186.

[16] Keynes, J. M. (2018). The general theory of employment, interest, and money. Springer.

[17] Kritzman, M., Li, Y., Page, S., & Rigobon, R. (2011). Principal components as a measure of systemic risk. The Journal of Portfolio Management, 37(4), 112-126.

[18] Lahmiri, S. (2014). Entropy-based technical analysis indicators selection for international stock markets fluctuations prediction using support vector machines. Fluctuation and Noise Letters, 13(02), 1450013.

[19] Li, J., Tsiakas, I., & Wang, W. (2015). Predicting exchange rates out of sample: Can economic fundamentals beat the random walk?. Journal of Financial Econometrics, 13(2), 293-341.

[20] Mariano, R. S., & Murasawa, Y. (2003). A new coincident index of business cycles based on monthly and quarterly series. Journal of applied Econometrics, 18(4), 427-443.

[21] Meese, R. A., & Rogoff, K. (1983). Empirical exchange rate models of the seventies: Do they fit out of sample?. Journal of international economics, 14(1-2), 3-24.

[22] Nassirtoussi, A. K., Wah, T. Y., & Ling, D. N. C. (2013). A novel FOREX prediction methodology based on fundamental data. African Journal of Business Management, 5(20), 8322-8330.

[23] Pandey, T. N., Jagadev, A. K., Dehuri, S., & Cho, S. B. (2018). A review and empirical analysis of neural networks based exchange rate prediction. Intelligent Decision Technologies, 12(4), 423-439.

[24] Pukthuanthong, K., & Roll, R. (2009). Global market integration: An alternative measure and its application. Journal of Financial Economics, 94(2), 214-232.

[25] Rojas, C. G., & Herman, M. (2018). Foreign exchange forecasting via machine learning.

[26] 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.

[27] Verdelhan, A. (2018). The share of systematic variation in bilateral exchange rates. The Journal of Finance, 73(1), 375-418.

[28] Williams, S., Fenn, D., & McDonald, M. (2012). Risk On-Risk Off. HSBC Global Research, April.

[29] Yıldırım, D. C., Toroslu, I. H., & Fiore, U. (2021). Forecasting directional movement of Forex data using LSTM with technical and macroeconomic indicators. Financial Innovation, 7(1), 1-36.

[30] Zhang, Z., & Khushi, M. (2020, July). GA-MSSR: Genetic Algorithm Maximizing Sharpe and Sterling Ratio Method for RoboTrading. In 2020 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE.