過去二十年來，全球化使得國際資金流量變得越來越方便因為其帶來了巨量的國際貿易。隨之而來的是海外金融市場增加了大量的投資。外匯交易市場擁有幾乎全天都能進行交易的特性，投資者能利用這種便利性投注資金在不同貨幣的利率差上，因此在許多不同的投資工具中，貨幣利差交易（carry trade）越來越受歡迎。近年來它已經成為一項利潤豐厚的業務，有一些國家為了刺激經濟而將利率降至接近於零，而其他國家仍然維持高利率來應對通貨膨脹，這造就了利率差的產生。在經濟相關的文獻中，大多數貨幣利差交易研究仍然使用線性回歸模型來研究貨幣利差交易的時間序列可預測性，而沒有識別資料集中可能存在的複雜非線性關係。本研究嘗試通過實作更複雜的人工神經網絡（ANN）模型來改變這種情況。我們將透過文獻探討確認預測利差交易收益的因子，然後採用能夠有效進行資料清理和機器學習的ANN機制來預測利差交易的回報。由於資料具有時間序列的特徵，我們增加移動視窗（moving window）在機制裡以利學習和忘記來增加預測資料的有效性。為了加速學習，我們還使用TensorFlow和GPU來實現ANN機制。

In the past two decades, globalization makes it easy for international cash flows because of huge volume of international trades. Along came the vast amount of foreign investments in the financial markets. Among those many different investment vehicles, currency carry trades became popular because foreign exchange markets now work around the clock and investors have used that convenience to take advantage of the difference between interest rates in different currencies. It has become a lucrative business in recent years because some countries cut their interest rates close to zero to stimulate their economy, while other countries still have high interest rates to combat inflation. In the economic literature of carry trades, most studies still use linear regression models to explore the time-series predictability of currency carry trades without identifying possible complex nonlinear relationships in data sets. This study tries to change that by implementing a more sophisticated Artificial Neural Networks (ANN) model. We connect the economic literature on the factors that predicts the profitability of carry trades and then adopt an ANN mechanism that can effectively conduct data cleaning and machine learning to predict the returns on carry trades. Since data has all time-series features, we add the moving window mechanism to facilitate learning and forgetting to increase the effectiveness of predictability. In order to speed up the learning, we also use TensorFlow and GPU to implement the ANN mechanism.

Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., . . . Isard, M. (2016). TensorFlow: A System for Large-Scale Machine Learning. Paper presented at the OSDI.
Adrian, T., Etula, E., & Shin, H. S. (2010). Risk appetite and exchange rates.
Asness, C. S., Moskowitz, T. J., & Pedersen, L. H. (2013). Value and momentum everywhere. The Journal of Finance, 68(3), 929-985.
Babaeizadeh, M., Frosio, I., Tyree, S., Clemons, J., & Kautz, J. (2016). Reinforcement learning through asynchronous advantage actor-critic on a gpu.
Bakshi, G., & Panayotov, G. (2013). Predictability of currency carry trades and asset pricing implications. Journal of Financial Economics, 110(1), 139-163.
Barzdins, G., Renals, S., & Gosko, D. (2016). Character-Level Neural Translation for Multilingual Media Monitoring in the SUMMA Project. arXiv preprint arXiv:1604.01221.
Bessembinder, H. (1994). Bid-ask spreads in the interbank foreign exchange markets. Journal of Financial Economics, 35(3), 317-348.
Bilson, J. F. (1981). The" speculative efficiency" hypothesis. Journal of Business, 54(3), 435–451.
Bilson, J. F. (2013). Adventures in the Carry Trade. Retrieved from http://www.cmegroup.com/education/files/bilson-adventures-in-the-carry-trade.pdf
Brunnermeier, M. K., Nagel, S., & Pedersen, L. H. (2008). Carry trades and currency crashes. NBER macroeconomics annual, 23(1), 313-348.
Burnside, C., Eichenbaum, M., Kleshchelski, I., & Rebelo, S. (2006). The returns to currency speculation. Retrieved from
Burnside, C., Eichenbaum, M., Kleshchelski, I., & Rebelo, S. (2010). Do peso problems explain the returns to the carry trade? The Review of Financial Studies, 24(3), 853-891.
Campbell, J. Y. (1990). A variance decomposition for stock returns. Retrieved from
Cenedese, G., Sarno, L., & Tsiakas, I. (2014). Foreign exchange risk and the predictability of carry trade returns. Journal of Banking & Finance, 42, 302-313.
Chen, Y.-C., Rogoff, K. S., & Rossi, B. (2010). Can exchange rates forecast commodity prices? The Quarterly Journal of Economics, 125(3), 1145-1194.
Clarida, R., Davis, J., & Pedersen, N. (2009). Currency carry trade regimes: Beyond the Fama regression. Journal of International Money and Finance, 28(8), 1375-1389.
Cumby, R. E., & Obstfeld, M. (1981). A note on exchange‐rate expectations and nominal interest differentials: A test of the Fisher hypothesis. The Journal of Finance, 36(3), 697-703.
Curcuru, S., Vega, C., & Hoek, J. (2010). Measuring carry trade activity. IFC Bulletin, 25, 436.
Dacorogna, M. M., Müller, U. A., Nagler, R. J., Olsen, R. B., & Pictet, O. V. (1993). A geographical model for the daily and weekly seasonal volatility in the foreign exchange market. Journal of International Money and Finance, 12(4), 413-438.
Daniel, K., Hodrick, R. J., & Lu, Z. (2017). The carry trade: Risks and drawdowns. Critical Finance Review, 6(2), 211-262.
Darvas, Z. (2009). Leveraged carry trade portfolios. Journal of Banking & Finance, 33(5), 944-957.
Engel, C. (1996). The forward discount anomaly and the risk premium: A survey of recent evidence. Journal of empirical finance, 3(2), 123-192.
Fama, E. F. (1984). Forward and spot exchange rates. Journal of monetary economics, 14(3), 319-338.
Gama, J., Žliobaitė, I., Bifet, A., Pechenizkiy, M., & Bouchachia, A. (2014). A survey on concept drift adaptation. ACM computing surveys (CSUR), 46(4), 44.
Groen, J. J., & Pesenti, P. A. (2011). Commodity prices, commodity currencies, and global economic developments. Paper presented at the Commodity Prices and Markets, East Asia Seminar on Economics, Volume 20.
Hansen, L. P., & Hodrick, R. J. (1980). Forward exchange rates as optimal predictors of future spot rates: An econometric analysis. Journal of political economy, 88(5), 829-853.
Hsieh, D. A., & Kleidon, A. W. (1996). Bid-ask spreads in foreign exchange markets: Implications for models of asymmetric information The Microstructure of Foreign Exchange Markets (pp. 41-72): University of Chicago Press.
Huang, S.-Y., Lin, J.-W., & Tsaih, R.-H. (2016). Outlier detection in the concept drifting environment. Paper presented at the Neural Networks (IJCNN), 2016 International Joint Conference on.
Huang, S.-Y., Yu, F., Tsaih, R.-H., & Huang, Y. (2014). Resistant learning on the envelope bulk for identifying anomalous patterns. Paper presented at the Neural Networks (IJCNN), 2014 International Joint Conference on.
Jurek, J. W. (2014). Crash-neutral currency carry trades. Journal of Financial Economics, 113(3), 325-347.
Kearns, J. (2007). Commodity currencies: why are exchange rate futures biased if commodity futures are not? Economic Record, 83(260), 60-73.
Lin, J.-W. (2015). A Decision Support Mechanism for Outlier Detection in the Concept Drifting Environment. (Unpublished Master Thesis), National Chengchi University, Taipei.
Lin, T. C. (2015). Infinite financial intermediation. Wake Forest L. Rev., 50, 643.
Lustig, H., Roussanov, N., & Verdelhan, A. (2011). Common risk factors in currency markets. The Review of Financial Studies, 24(11), 3731-3777.
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.
Mishkin, F. S. (2006). Economics of Money, Banking, and Financial Markets. Boston, MA: Addison-Wesley.
Niimi, T. (2016). Recent Trends in Foreign Exchange (FX) Margin Trading in Japan. Retrieved from
Parloff, R. (2016). Why Deep learning is suddenly changing your life. Retrieved from http://fortune.com/ai-artificial-intelligence-deep-machine-learning
Puri, M., Pathak, Y., Sutariya, V. K., Tipparaju, S., & Moreno, W. (2015). Artificial Neural Network for Drug Design, Delivery and Disposition: Academic Press.
Rasmussen, C. E. (2004). Gaussian processes in machine learning Advanced lectures on machine learning (pp. 63-71): Springer, Berlin, Heidelberg.
Robert C. Feenstra, A. M. T. (2008). International Macroeconomics. New York, NY: Worth Publishers.
Sarno, L. (2005). Towards a solution to the puzzles in exchange rate economics: Where do we stand? Canadian Journal of Economics/Revue canadienne d'économique, 38(3), 673-708.
Shehadeh, A., Erdős, P., Li, Y., & Moore, M. (2016). US Dollar Carry Trades in the Era of'Cheap Money'. Retrieved from SSRN: https://ssrn.com/abstract=2765552 or http://dx.doi.org/10.2139/ssrn.2765552
Sill, K. (2000). Understanding asset values: stock prices, exchange rates, and the “Peso Problem”. Business review.
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., . . . Rabinovich, A. (2015). Going deeper with convolutions.
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013). Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199.
Terada, T., Higashio, N., & Iwasaki, J. (2008). Recent trends in Japanese foreign-exchange margin trading. Exchange, 200, 250.
Trippi, R. R., & Turban, E. (1992). Neural networks in finance and investing: Using artificial intelligence to improve real world performance: McGraw-Hill, Inc.
Tsaih, R.-H., & Cheng, T.-C. (2009). A resistant learning procedure for coping with outliers. Annals of Mathematics and Artificial Intelligence, 57(2), 161-180.
Tu, J. V. (1996). Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. Journal of clinical epidemiology, 49(11), 1225-1231.
Wu, J. (2017). Application of Machine Learning to Predicting the Returns of Carry Trade. (Unpublished Master Thesis), National Chengchi University, Taipei.