- 學位論文
利差交易之風險溢酬預測－長短期記憶神經網路之應用
Predicting the Risk Premium of Carry Trade with LSTM Neural Network
摘要
外匯市場是全球金融體系當中重要的一環，利差交易為投機客、外匯交易員、避險基金等在外匯市場當中普遍採用的交易策略。近年來，新興市場貨幣在利差交易中所佔份額逐漸增加，由於新興市場利率普遍高於成熟市場，其獲利可能性使得外匯市場參與者蜂擁而至，然而，匯率之劇烈波動卻可能侵蝕掉賺取的利潤。 傳統利率模型僅以遠期溢價預測匯率變動，但在實證結果上卻往往與理論相悖離，因此，本研究將國家風險因素納入考量，並將機器學習中的類神經網路概念及技術引入金融領域當中，以長短期記憶模型(LSTM)對未來匯率變動進行預測，同時也將其預測能力與傳統迴歸模型之預測效果相互比較。實證發現，在新興市場國家當中使用LSTM神經網路模型，並以考量國家風險因子之遠期溢價預測未來匯率走勢有較傑出的預測效果。除了將類神經網路用以預測匯率變動之外，我們一樣能將人工智慧的技術應用於其他金融商品之價格預測上，隨著技術日漸進步、人工智慧相關領域的研究逐年倍增，數以萬計的應用場景將在人工智慧的環境下得以升級。
並列摘要
The foreign exchange market plays an important role in the global financial system. Carry Trade is one of the most popular trading strategies for speculators, forex traders, hedge funds, etc. In recent years, emerging market currencies gained market share gradually. Owing to the interest spread between emerging markets and developed markets, lots of foreign exchange market participants attracted by the profitability. However, the volatility of exchange rates might cause profit erosion. Uncovered Interest Rate Parity (UIP) only use the forward premium to predict the changes in the foreign exchange rate, but empirical results often deviate from the theoretical studies. Therefore, this study introduces the country risk factor into the UIP equation. Adopting the concept of neural networks into the financial field, we use Long Short-Term Memory (LSTM) neural network for the foreign exchange rate prediction. Then, compares its predictive ability to the traditional regression model’s. According to the empirical study, we predict the future trend of the foreign exchange rate in the emerging markets. By using the forward premium with the country risk, LSTM neural network shows the outstanding result. Besides the implementation of currency forecasting via neural networks, Artificial Intelligence (AI) technologies can also apply to other financial products’ price prediction. With the advances of technology and AI, thousands of application scenarios will be able to be promoted.