Loading...
|
Please use this identifier to cite or link to this item:
https://nccur.lib.nccu.edu.tw/handle/140.119/145836
|
| Title: | 使用 LSTM 結合匯率模型和技術指標預測外匯走勢
Forecasting Foreign Exchange Trends using LSTM with Exchange Rate Model and Technical Indicators |
| Authors: | 廖浲諭
Liao, Feng-Yu |
| Contributors: | 蕭明福
廖四郎
Shaw, MingFu
Liao, Szu-Lang
廖浲諭
Liao, Feng-Yu |
| Keywords: | LSTM
外匯預測
匯率模型
總經指標
技術指標
LSTM
Foreign Exchange Forecasting
Exchange Rate Models
Macroeconomic Indicators
Technical Indicators |
| Date: | 2023 |
| Issue Date: | 2023-07-06 16:41:14 (UTC+8) |
| Abstract: | 本研究嘗試結合總體經濟和技術指標的特性來預測外匯走勢，利用長短期記憶模型(LSTM)以總體指標和技術指標作為輸入變數，進行外匯漲跌方向的預測，總體指標參考4個匯率模型UIRP、PPP、MF和Taylor Rule作為挑選變數，將總體指標與技術指標分開預測再進行結合，比較此作法是否優於個別分開預測，且能觀察模型改善的效果的好壞，最後會對模型進行績效評估。
實證結果顯示，總經指標使用LSTM以 PPP和Taylor Rule作為變數預測結果優於以UIRP和MF作為變數，以PPP和Taylor Rule為基底加入台灣外匯存底月變動和大盤月報酬變動 2個變數後，預測表現皆下降但報酬率皆上升，技術指標再經過篩選後以開盤價、最高價、最低價、CCI、MOM作為變數預測表現較佳，結合模型後相較於個別預測有明顯改善，以PPP結合技術模型準確率最高、Taylor Rule結合技術模型準確率次高，在績效評估上以Taylor Rule結合技術模型表現最佳，模型改善效果以Taylor Rule改善最大。
This study attempts to combine the characteristics of macroeconomic indicators and technical indicators to predict foreign exchange trends. It utilizes the LSTM with macroeconomic and technical indicators as input variables to forecast the direction of foreign exchange movements. The macroeconomic indicators are based on four exchange rate models: UIRP, PPP, MF, and Taylor Rule. The study compares the performance of combined forecasting with separately predicting macroeconomic and technical indicators to assess the effectiveness of the proposed approach.
The empirical results demonstrate that using LSTM with PPP and Taylor Rule as variables yields superior predictions compared to using UIRP and MF. When incorporating two additional variables, the monthly changes in Taiwan`s foreign exchange reserves and stock market returns, based on PPP and Taylor Rule, the prediction performance decreases while the return rates increase. After filtering, the selected technical indicators including opening price, high price, low price, CCI, and MOM exhibit better predictive performance. The combined model shows significant improvements compared to individual predictions, with the highest accuracy achieved by combining PPP with the technical model and the second-highest accuracy achieved by combining Taylor Rule with the technical model. In terms of performance evaluation, the combined model of Taylor Rule and the technical indicators performs the best, and Taylor Rule contributes the most to the improvement in model performance. |
| Reference: | [1] Allen, H. and M. P. Taylor (1992), “The Use of Technical Analysis in the Foreign Exchange Market,” Journal of International Money and Finance, Vol. 113, 301-314.
[2] Amat, C., Michalski, T., and Stoltz, G. (2018). Fundamentals and exchange rate forecastability with simple machine learning methods. Journal of International Money and Finance, 88, 1-24.
[3] Chen, Yu-chin, and Kenneth Rogoff, 2003, "Commodity Currencies," Journal of Internationa Economics, Vol. 60, pp. 133-60
[4] Engel, C. and K. D. West, (2005). Exchange Rates and Fundamentals, Journal of Political Economy. 113: 485-517.
[5] Engel, C., Mark, N. C. and West, K. D. (2015). “Factor model forecasts of exchange rates.” Econometric Reviews, 34, 32-55
[6] Frenkel, J. A. (1976). “A monetary approach to the exchange rate.” Scandinavian J. Econ. 78, no.2, 200-224.
[7] Fischer, T., and Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654-669.
[8] Gourinchas, P.-O., and Rey, H. (2007). International financial adjustment. Journal of Political Economy, 115(4), 665-703.
[9] Hau, H., and Rey, H. (2006). Exchange rates, equity prices, and capital flows. Review of Financial Studies 19, 273-317.
[10] Hodrick, R. J., and Prescott, E. C. (1997). Postwar US business cycles: an empirical investigation. Journal of Money, credit, and Banking, 1-16.
[11] Mark, Nelson C. (1995), “Exchange Rate and Fundamentals: Evidence on Long-Horizon Predictability,” American Economimc Review, 85, 201-218.
[12] Mark, N. C. and D. Sul, (2001). Nominal Exchange Rates and Monetary Fundamentals: Evidence from a Small Post-bretton Woods Panel. Journal of International Economics, 53: 29-52.
[13] Molodtsova, T. and D. H. Papell, (2009). Out-of-Sample Exchange Rate Predictability with Taylor Rule Fundamentals? Journal of International Economics, 77: 167-180.
[14] Meese, Richard A. and Kenneth Rogoff (1983), “Empirical Exchange Rate Models of the Seventies: Do They Fit Out of Sample?” Journal of International Economics, 14, 3-24.
[15] Nelson,M.Q., Pereira, A.C.M. and deOliveira,R.A. (2017). Stockmarketsprice movement prediction with LSTM neural networks. International Joint Conference on Neural Networks (IJCNN). Piscataway, NJ: IEEE, pp. 1419-1426.
[16] Qu, Y., and Zhao, X. (2019). Application of LSTM neural network in forecasting foreign exchange price. In Journal of Physics: Conference Series (Vol. 1237, No. 4, p. 042036). IOP Publishing.
[17] Rossi, B. (2013). Exchange rate predictability. Journal of economic literature, 51(4), 1063-1119.
[18] Yıldırım, D. C., Toroslu, I. H., and Fiore, U. (2021). Forecasting directional movement of Forex data using LSTM with technical and macroeconomic indicators. Financial Innovation, 7, 1-36. |
| Description: | 碩士
國立政治大學
經濟學系
110258034 |
| Source URI: | http://thesis.lib.nccu.edu.tw/record/#G0110258034 |
| Data Type: | thesis |
| Appears in Collections: | [經濟學系] 學位論文
|
Files in This Item:
| File |
Description |
Size | Format | |
|---|
| 803401.pdf | | 2473Kb | Adobe PDF2 | 0 | View/Open |
|
All items in 政大典藏 are protected by copyright, with all rights reserved.
|
