New hybrid fuzzy time series model: Forecasting the foreign exchange market

• José Eduardo Medina Reyes ^[1] ; Salvador Cruz Aké ^[1] ; Agustín Ignacio Cabrera Llanos ^[1]
  1. [1] Instituto Politécnico Nacional

     Instituto Politécnico Nacional

     México

     
• Localización: Contaduría y administración, ISSN 0186-1042, ISSN-e 2448-8410, Vol. 66, Nº. 3, 2021
• Idioma: inglés
• DOI: 10.22201/fca.24488410e.2021.2623
• Títulos paralelos:
  • Nuevo modelo híbrido de series de tiempo difusas: pronosticando el mercado de divisas
• Enlaces
  • Texto completo (pdf)
• Resumen
  • español

    Este trabajo desarrolla una comparación entre la predicción de volatilidad de los modelos tradicionales de series de tiempo (ARIMA, EGARCH y PARCH), contra dos nuevos modelos propuestos basados en la teoría difusa (FTS-Fuzzy ARIMA Tseng y FTS-Fuzzy ARIMA Tanaka). Para hacer esta comparación, estimamos el rendimiento del tipo de cambio peso mexicano - dólar estadounidense desde enero de 2008 hasta diciembre de 2017. Nuestro resultado principal es que los modelos basados en la teoría difusa generan una mejor estimación de la volatilidad. Los modelos difusos muestran un menor error de pronóstico que la serie de tiempo tradicional en ambos; dentro y fuera de las pruebas de muestra;

    para la volatilidad en el rendimiento del tipo de cambio peso mexicano - dólar estadounidense. Por lo tanto, los modelos difusos mostraron una mayor eficiencia y reflejan mejor la información del mercado.

  • English

    This work develops a comparison between the volatility prediction of traditional time series models (ARIMA, EGARCH and PARCH), against two new proposed models based on fuzzy theory (FTSFuzzy ARIMA Tseng’s and FTS-Fuzzy ARIMA Tanaka’s). To make this comparison, we estimated the Mexican peso - US dollar exchange rate yield from January 2008 to December 2017. Our main result is that the models based on fuzzy theory generate a better estimate of the volatility. The fuzzy models show a smaller least forecast error than the traditional time series in both; in and out of sample tests; for the volatility in the yield of the Mexican peso – US dollar exchange rate. Therefore, the fuzzy models showed higher efficiency and better reflects the market information.

• Referencias bibliográficas
  • Chen, S. M., & Hsu, C. C. (2004). A new method to forecast enrollments using fuzzy time series. International Journal of Applied Science...
  • Chen, S.-M. (1996). Forecasting enrollments based on fuzzy time series. Fuzzy Sets and Systems, 81, 311-319. Retrieved from https://ir.nctu.edu.tw/bitstream/11536/1108/1/A1996VB35900002.pdf
  • Egrioglu, E., Aladag, C. H., Yolcu, U. B., A., M., & Uslu, V. R. (2009). A new hybrid approach based on SARIMA and partial high order...
  • Guney, H., Bakir, M. A., & Aladag, C. H. (2017). A Novel Stochastic Seasonal Fuzzy Time Series Forecasting Model. International Journal...
  • Ishibuchi, H., & Tanaka, H. (1992). Fuzzy regression analysis using neural networks. Fuzzy sets and systems, 50(3). doi:https://doi.org/10.1016/0165-0114(92)90224-R
  • Pal, S. S., & Kar, S. (2017). Fuzzy Time Series Model for Unequal Interval Length Using Genetic Algorithm. Advances in Intelligent Systems...
  • Pal, S. S., & Kar, S. (2019). A Hybridized Forecasting Method Based on Weight Adjustment of Neural Network Using Generalized Type-2 Fuzzy...
  • Popov, A., & Bykhanov, K. (2005). Modeling Volatility of Time Series Using Fuzzy GARCH Models. Science and Technology, 687-692. doi:10.1109/KORUS.2005.1507875
  • Silva, P. C., Sadaei, H. J., Ballini, R., & Guimaraes, F. G. (2019). Probabilistic Forecasting With Fuzzy Time Series. IEEE Transactions...
  • Singh, P. (2017). A brief review of modeling approaches based on fuzzy time series. International Journal of Machine Learning and Cybernetics,...
  • Song, Q., & Chissom, B. S. (1993a). Fuzzy time series and its models. Fuzzy Sets and Systems, 54, 269- 277. Retrieved from https://www.researchgate.net/profile/Qiang_Song6/publication/256410485_Fuzzy_time_series_and_its_model/links/5a0055080f7e9b62a14d2b54/Fuzzy-time-series-and-its-model.pdf
  • Song, Q., & Chissom, B. S. (1993b). Forecasting enrollments with fuzzy time series — Part I. Fuzzy Sets and Systems, 54, 1-9. Retrieved...
  • Song, Q., & Chissom, B. S. (1994). Forecasting enrollments with fuzzy time series part II. Fuzzy Sets and Systems, 62, 1-8. Retrieved...
  • Souza, P. V., & Torres, L. C. (2018). Regularised Fuzzy Neural Network Based on Or Neuron for Time Series Forecasting. Fuzzy Information...
  • Tanaka, H. (1987). Fuzzy Data Analysis by Possibilistic Linear. Fuzzy Sets and Systems, 363-375. doi:https://doi. org/10.1016/0165-0114(87)90033-9
  • Tanaka, H., Asai, K., & Uejima, S. (1982). Linear Regression Analysis with Fuzzy Model. IEEE Transactions On Systems, Man, and Cybernetics,...
  • Tsaur, R.-C. (2012). A Fuzzy Time Series-Markov Chain Model with an Application to Forecast the Exchange Rate Between the Taiwan and US Dollar....
  • Tseng, F.-M., & Tzeng, G.-H. (2002). A fuzzy seasonal ARIMA model for forecasting. Fuzzy Sets and Systems, 126(3), 367-376. doi:10.1016/S0165-0114(01)00047-1
  • Tseng, F.-M., Tzeng, G.-H., Yu, H.-C., & Yuan, B. J. (2009). Fuzzy ARIMA model for forecasting the foreign exchange market. Fuzzy Sets...
  • Xiao, Q. (2017). Time Series Prediction Using Bayesian Filtering Model and Fuzzy Neural Networks. Optik, 140, 104-113. doi:https://doi.org/10.1016/j.ijleo.2017.03.096
  • Yu, T. H.-K., & Huarng, K.-H. (2012). A neural network-based fuzzy time series model to improve forecasting. Expert Systems with Applications,...