Forecasting Daily and Monthly Exchange Rates with Machine Learning Techniques

Abstract

In this paper we propose and test a forecasting model on monthly and daily spot prices of five selected exchange rates. In doing so, we combine a novel smoothing technique (initially applied in signal processing) with a variable selection methodology and two regression estimation methodologies from the field of machine learning (ML). After the decomposition of the original exchange rate series using an ensemble empirical mode decomposition (EEMD) method into a smoothed and a fluctuation component, multivariate adaptive regression splines (MARS) are used to select the most appropriate variable set from a large set of explanatory variables that we collected. The selected variables are then fed into two distinctive support vector machines (SVR) models that produce one‐period‐ahead forecasts for the two components. Neural networks (NN) are also considered as an alternative to SVR. The sum of the two forecast components is the final forecast of the proposed scheme. We show that the above implementation exhibits a superior in‐sample and out‐of‐sample forecasting ability when compared to alternative forecasting models. The empirical results provide evidence against the efficient market hypothesis for the selected foreign exchange markets. Copyright © 2015 John Wiley & Sons, Ltd.

The depreciation of the pound post-Brexit: Could it have been predicted?

“…Thus, in our study apart from linear Ordinary Least Square models we also examine the nonlinear Support Vector Regression (SVR) methodology (Vapnik et al, 1992). The high forecasting ability of the methodology has attracted significant interest in forecasting economics and financial time series (Rubio et al, 2011;Plakandaras et al, 2015).…”

“…The decision to use a nonlinear approach emanates from the wide-spread evidence of nonlinearity in the behavior of the exchange rate on its own and in its relationship with its predictors (Balcilar et al, 2016). We employ a machine learning framework (Support Vector Regressions) in our paper to capture nonlinearity, motivated by the recent evidence of superior exchange rate forecasts produced by this type of model, as provided by Plakandaras et al, (2015).…”

Determinants of Commodity Futures Prices: Decomposition Approach

“…Researchers have applied EMD in studies on economic and financial data. It has been applied, for example, in modeling agricultural products (Wang et al [13]; Abadan and Shabri [19]), electricity price (Xiong et al [20]; An et al [21]; Crosato et al [22]), on exchange rates (Lin et al [23]; Premanode and Toumazou [24]; Plakandaras et al [25]), gold prices (Jian-Hui and Wei [26]; Hua and Jiang [27]; Owusu Junior et al [28]), crude oil prices (Meng et al [29]; Chen et al [30]; Yu et al [31]; Zhang et al [32]; Wu and Huang [33], and on carbon prices (Zhu et al [12]). Premanode and Toumazou [24] used differential empirical mode decomposition (DEMD) for improving forecasting of exchange rates using the support of vector regression (SVR).…”

Efficiency in BRICS Currency Markets Using Long-Spans of Data: Evidence from Model-Free Tests of Directional Predictability

“…The second question deals with why we look at directional predictability instead of the conditional mean of the foreign exchange rate changes? The reasons behind this, as outlined in Chung and Hong (2007), and also in Plakandaras et al (2013Plakandaras et al ( , 2015a, are: (a) From the perspective of a statistician, it is relatively easier to predict the direction of changes than the predictions of the conditional mean, as directional predictability depends on all conditional moments; (b) From an economist's point of view, the directional predictability of foreign exchange rate returns is more relevant as it is better able to capture a utility-based measure of predictability performance (such as economic profits). In addition, note that market timing (a form of active asset allocation management) is essentially the prediction of turning points in currency markets; (c) Direction of changes provide important insights to market practitioners and policymakers, Since technical trading rules widely used by foreign exchange dealers are heavily based on predictions of direction of changes, and central banks.…”

“…In light of the importance of currency markets, efficiency of the same has been examined extensively, since the seminal work of Meese and Rogoff, (1983), with the widespread acceptance that it is difficult to beat the random walk model in predicting the conditional mean dynamics of foreign exchange rate changes (see for example, Chung and Hong, (2007), Charles et al, (2012), Plakandaras et al, (2013Plakandaras et al, ( , 2015a, Balcilar et al, (2016), Papadimitriou et al, (2016), Almail and Almudhaf (2017), and Christou et al, (forthcoming) for detailed reviews of this literature). However, the majority of these studies are based on the tests of some forecast models or forecast rules, i.e., these works examine the efficiency of models rather than data, and as a result, the conclusions are dependent on the model used.…”