A Kalman filter-based hybridization model of statistical and intelligent approaches for exchange rate forecasting. (4th September 2020)

• Record Type: Journal Article
• Authors: Khashei, Mehdi; Mahdavi Sharif, Bahareh
• Is Part Of: Journal of modelling in management. Volume 16:Number 2(2021)
• Page Start: 579
• Page End: 601
• Publication Date: 2020-09-04
• Subjects: Finance -- Artificial intelligence -- Statistics -- Forecasting -- Neural networks -- Multinational firms -- Artificial neural networks (ANNs) -- Auto-regressive integrated moving average (ARIMA) -- Kalman filter preprocessing technique -- Time series models -- Exchange rate forecasting; Industrial management -- Mathematical models -- Periodicals; Industrial management -- Computer simulation -- Periodicals; Business -- Mathematical models -- Periodicals; Business -- Computer simulation -- Periodicals; 658.4033
• DOI: 10.1108/JM2-12-2019-0277
• Languages: English
• ISSNs: 1746-5664

Abstract

Abstract : Purpose: The purpose of this paper is to propose a comprehensive version of a hybrid autoregressive integrated moving average (ARIMA), and artificial neural networks (ANNs) in order to yield a more general and more accurate hybrid model for exchange rates forecasting. For this purpose, the Kalman filter technique is used in the proposed model to preprocess and detect the trend of raw data. It is basically done to reduce the existing noise in the underlying data and better modeling, respectively. Design/methodology/approach: In this paper, ARIMA models are applied to construct a new hybrid model to overcome the above-mentioned limitations of ANNs and to yield a more general and more accurate model than traditional hybrid ARIMA and ANNs models. In our proposed model, a time series is considered as a function of a linear and nonlinear component, so, in the first phase, an ARIMA model is first used to identify and magnify the existing linear structures in data. In the second phase, a multilayer perceptron is used as a nonlinear neural network to model the preprocessed data, in which the existing linear structures are identified and magnified by ARIMA and to predict the future value of time series. Findings: In this paper, a new Kalman filter based hybrid artificial neural network and ARIMA model are proposed as an alternate forecasting technique to the traditional hybrid ARIMA/ANNs models. In the proposed model, similar to the traditional hybrid ARIMA/ANNs models, the unique strengths of ARIMA and ANN in linear and nonlinear modeling are jointly used, aiming to capture different forms of relationship in the data; especially, in complex problems that have both linear and nonlinear correlation structures. However, there are no aforementioned assumptions in the modeling process of the proposed model. Therefore, in the proposed model, in contrast to the traditional hybrid ARIMA/ANNs, it can be generally guaranteed that the performance of the proposed model will not be worse than either of their components used separately. In addition, empirical results in both weekly and daily exchange rate forecasting indicate that the proposed model can be an effective way to improve forecasting accuracy achieved by traditional hybrid ARIMA/ANNs models. Originality/value: In the proposed model, in contrast to the traditional hybrid ARIMA/ANNs, it can be guaranteed that the performance of the proposed model will not be worse than either of the components used separately. In addition, empirical results in exchange rate forecasting indicate that the proposed model can be an effective way to improve forecasting accuracy achieved by traditional hybrid ARIMA/ANNs models. Therefore, it can be used as an appropriate alternate model for forecasting in exchange ratemarkets, especially when higher forecasting accuracy is needed.