ตัวแบบพยากรณ์อัตราแลกเปลี่ยนสกุลเงิน

Main Article Content

ธรณินทร์ สัจวิริยทรัพย์

Abstract

The objective of this research was to investigate the most suitable forecasting model for three currency exchange rates (e.g. USD, SGD and JPY), which are time series from August 2012 to July 2017. The comparative study was used to find the most proper forecasting model from six forecasting models (e.g. simple exponential smoothing, Additive Holt-Winters, Multiplicative Holt-Winters, ARIMA, ARFIMA, and Feed-forward artificial neural network) based on five accuracy measures. The most suitable forecasting model plays a crucial role in international trade as well as effective import-export strategies of Thailand. The empirical results indicated that the feed–forward neural network outperforms all five statistical forecasting models, which revealed that the patterns of three currency exchange rates follow non-linear pattern rather than linear pattern. In addition, the developed model is formulated based on a few prior assumptions compared to statistical forecasting models. The model is able to construct complex predictive model to describe the currency exchange rates better than statistical forecasting models. Therefore, the proposed model can be a promising tool to predict the currency exchange rates, and to support decision making on effective import-export strategies of Thailand.

Downloads

Download data is not yet available.

Article Details

Section
วิทยาศาสตร์กายภาพ
Author Biography

ธรณินทร์ สัจวิริยทรัพย์

สาขาวิศวกรรมโลจิสติกส์ คณะวิศวกรรมศาสตร์ มหาวิทยาลัยหอการค้าไทย ถนนวิภาวดีรังสิต แขวงรัชดาภิเษก เขตดินแดง กรุงเทพมหานคร 10400

References

[1] Department of Trade Negotiations, Annual Report, Available Source: https://www.dtn.go.th/images/297/Trade/TRADE_2559.pdf, 12 September 2017.
[2] Rangkakulnuwat, P., 2008, Application of vector error correction model in forecasting exchange rates, Appl. Econ. J. 15(2): 19-31. (in Thai)
[3] Rout, M., Majhi, B., Majhi, R. and Panda, G., 2014, Forecasting of currency exchange rates using an adaptive ARMA model with differential evolution based training, J. King Saud Univ. Comp. Inform. Sci. 26: 7-18.
[4] Uyen Ngan, T.M., 2016, Forecasting foreign exchange rate by using ARIMA model: A case of VND/USD exchange rate, Res. J. Finance Account. 7(12): 38-44.
[5] Babu, A.S. and Reddy, S.K., 2015, Exchange rate forecasting using ARIMA, neural network and fuzzy neuron, J. Stock Forex Trading 4(3): 1-5.
[6] Adebiyi, A.A., Adewumi, A.O. and Ayo, C.K., 2014, Comparison of ARIMA and artificial neural networks models for stock price prediction, J. Appl. Math. 2014: 1-7.
[7] Maria, F.C. and Eva, D., 2011, Exchange-Rates Forecasting: Exponential smoothing techniques and ARIMA models, Ann. Fac. Econ. 1: 499-508.
[8] Liu, B.X., Wu, Y. and Cheng, X., 2013, RMB exchange rate forecasting model based on exponential smoothing and gray correlation, Appl. Mech. Mater. 401: 1480-1483.
[9] Yoon, G., 2010, Do real exchange rates really follow threshold autoregressive or exponential smooth transition auto regressive models?, Econ. Model. 27: 605-612.
[10] Lawton, R., 1998, How should additive Holt–Winters estimates be corrected?, Int. J. Forecast. 14: 393-403.
[11] Yıldıran, C.U. and Fettahoğlu, A., 2017, Forecasting USDTRY rate by ARIMA method, Cogent Econ. Finance 5: 1-11.
[12] Nwankwo, S.C., 2014, Autoregressive integrated moving average (ARIMA) model for exchange rate (Naira to Dollar), Acad. J. Interdiscip. Stud. 3: 429-433.
[13] Omekara, C.O., Okereke, O.E. and Ehighibe, S.E., 2016, Time series analysis of interest rate in Nigeria: A comparison of ARIMA and state space models, Int. J. Prob. Stat. 5: 33-47.
[14] Shittu O.I. and Yaya, O.S., 2009, Measuring forecast performance of ARMA & ARFIMA models: An application to US Dollar/UK pound foreign exchange rate. Eur. J. Sci. Res. 32: 167-176.
[15] Xiu, J. and Jin, Y., 2007, Empirical study of ARFIMA model based on fractional differencing, Phys. A Stat. Mech. Appl. 377: 138-154.
[16] Bhardwaj, G. and Swanson, N.R., 2006, An empirical investigation of the usefulness of ARFIMA models for predicting macroeconomic and financial time series, J. Econ. 131: 539-578.
[17] Sadaei, H.J., Enayatifar, R., Guimarães, F.G., Mahmud, M. and Alzamil, Z.A., 2016, Combining ARFIMA models and fuzzy time series for the forecast of long memory time series, Neurocomputing 175: 782-796.
[18] Singh, R.B., Gould, J., Chan, F. and Yang, J.W., 2016. Liquidation discount: A novel application of ARFIMA-GARCH, J. Emp. Finance 36: 151-161.
[19] Panda, C. and Narasimhan, V., 2007, Forecasting exchange rate better with artificial neural network, J. Pol. Model. 29: 227-236.
[20] Rehman, M., Khan, G.M. and Mahmud, S.A., 2014, Foreign currency exchange rates prediction using cgp and recurrent neural network, IERI Proc. 10: 239-244.
[21] Yu, L., Wang, S. and Lai, K.K., 2005, A novel nonlinear ensemble forecasting model incorporating GLAR and ANN for foreign exchange rates, Comp. Operations Res. 32: 2523-2541.
[22] Moghaddam, A.H., Moghaddam, M.H. and Esfandyari, M., 2016, Stock market index prediction using artificial neural network, J. Econ. Finance Admin. Sci. 21: 89-93.
[23] Majhi, R., Panda, G. and Sahoo, G., 2009, Efficient prediction of exchange rates with low complexity artificial neural network models, Exp. Syst. Appl. 36: 181-189.
[24] Thakur, G.S.M., Bhattacharyya, R. and Mondal, S.S., 2016, Artificial neural network based model for forecasting of inflation in India, Fuzzy Inform. Eng. 8: 87-100.
[25] Aydin, A.D. and Cavdar, S.C., 2015, Comparison of prediction performances of artificial neural network (ANN) and vector autoregressive (VAR) Models by using the macroeconomic variables of gold prices, Borsa Istanbul (BIST) 100 index and US Dollar-Turkish Lira (USD/TRY) exchange rates, Proc. Econ. Finance 30: 3-14.
[26] Bank of Thailand, Rates of Exchange of Commercial Banks, Available Source: https://www2.bot.or.th/statistics/ReportPage.aspx?reportID=123&language=th, 12 September 2017.
[27] Khandakar, Y. and Hyndman, R.J., 2008, Automatic time series forecasting: the forecast Package for R, J. Stat. Software 27(3): 1-22.
[28] Muller, J. and Bogenberger, K., 2015, Time series analysis of booking data of a free-floating carsharing system in Berlin, Transport. Res. Proc. 10: 345-354.
[29] Kokic, P., Crimp, S. and Howden, M., 2014, A probabilistic analysis of human influence on recent record global mean temperature changes, Climate Risk Manag. 3: 1-12.
[30] Ghodhi, Z., Silva, S.E. and Hassani, H., 2015, Bicoid signal extraction with a selection of parametric and nonparametric signal processing techniques, Genom. Proteom. Bioinform. 13: 183-191.
[31] Sujjaviriyasup, T., 2018, Artificial neural network model for forecasting monthly price of maize in Thailand, Srinakharin wirot Sci. J. 34(1): 91-107. (in Thai)
[32] Giam, X. and Olden, J.D., 2015, A new R2-based metric to shed greater insight on variable importance in artificial neural networks, Ecol. Model. 313: 307-313.
[33] Montoye, A.H., Pivarnik, J.M., Mudd, L.M., Biswas, S. and Pfeiffer, K.A., 2017, Evaluation of the activPAL accelerometer for physical activity and energy expenditure estimation in a semi-structured setting, J. Sci. Med. Sport 20: 1003-1007.