As a result, SVR works well for large datasets and can handle a large number of input variables without deletion. The most significant advantage of RF is its versatility. In fact, ensemble methods have been neglected in the existing literature on foreign currency market predictions even though ensemble methods are very powerful in reducing the variance inherently present in complex and volatile financial markets Carta et al. This study shows that the proposed ensemble deep learning approach provides a robust prediction performance, performing well for different clusters of time-series data in our study.
Our study analyses the prediction performance by clustering data based on the waves of confirmed COVID cases and on the timing of fiscal and monetary policies meant to combat the economic consequences of the COVID pandemic. All algorithms are applied for each dataset, the prediction performances are taken separately, and the accuracy curve is generated.
In predicting the foreign currency exchange rate, we measured the performance of the algorithms using the root mean square error RMSE , mean absolute error MAE , and mean absolute percentage error MAPE. The rest of the paper is organized as follows.
Section 2 briefly reviews existing research work on predicting the foreign exchange market and the impact of COVID on this market. Section 3 presents our experimental design and the data used for experiments. Section 5 presents the experimental analysis, and Sect. The results are discussed in Sect.
This section reviews previous studies on predicting the forex exchange market and provides the theoretical justification for investigating the impact of COVID on the predictability of foreign exchange markets. Model specification is required for the former category of models, and it limits their accuracy because many nonlinear time-series patterns cannot be captured.
Because advanced machine learning methods, such as support vector machine SVM and neural networks NNs outperformed the traditional parametric models in recent studies, we present these approaches in Table 1. Among the advanced machine learning methods, SVM and extreme learning machines were particularly effective when handling multidimensional time-series data obtained by using technical indicators for preprocessing.
However, these machine learning methods were proven ineffective when handling large and noisy data Munkhdalai et al. In contrast, LSTM-based models were highly effective due to their capacity to capture high-level temporal features from the foreign exchange time-series data Ahmed et al. The main limitation of existing approaches is that only single LSTMs were used without considering both previous and future data patterns, something that is needed to effectively learn long-term dependencies in the data.
Several studies revealed a significant impact of COVID on the volatility of foreign exchange markets. Hofmann et al. As a result, portfolio investors faced amplified losses. The dataset came from Kaggle and Oanda. Footnote 1 We used 21 currency exchange rates against USD. The dataset description is provided in Table 2.
Data clusters were divided based on the number of confirmed cases in the United States and the timeline of events related to the COVID pandemic. The experimental datasets were divided into training and testing sets. The training-to-testing ratio was The training set of the pre-COVID dataset was cross validated tenfold to minimise the training error and enhance the generalizability of the forecasting outcome Abedin et al.
Statistical models, machine learning, and deep learning models have been used in the literature to predict financial asset prices Abedin et al. We apply machine learning and deep learning algorithms to measure different types of errors and find the best model for the dataset to measure the prediction accuracy for each currency against USD.
Different algorithms have been used to select the best method to calculate the prediction error of exchange rate movements of the selected currencies. Footnote 2 , Footnote 3. Using a decision tree is a common practical approach for supervised learning Chen, ; Delen et al.
It is used for both classification and regression estimations. The decision tree is a tree-structured classifier that consists of three types of nodes, namely, the root node, interior node, and leaf node. The root node is the initial node that represents the whole sample. The interior nodes represent the characteristics of a data set.
Lastly, the root nodes provide the outcome. The final prediction is calculated by finding the average value of a dependent variable in a specific leaf node. In this way, the tree can predict a proper value for the data point through several iterations Fig. The decision tree is advantageous because it is simple to understand and requires less data cleaning. Like ridge and lasso regression, decision tree regression may have overfitting problems.
An ensemble of decision trees e. This is a supervised machine learning algorithm used for classification and regression purposes Weston et al. This study applies three different kernels, linear, polynomial, and radial basis function RBF , while training the SVR classifier. SVR makes a decision boundary based on the support vector points and, accordingly, it forecasts sample points within this boundary.
Random forest is an ensemble algorithm that builds a set of independent and non-identical decision trees following the idea of randomisation Provost et al. This algorithm is used for both classification and regression purposes, and it is a combination of tree predictors. Each decision tree employs a random vector as a parameter randomly chooses the attributes of samples, and it then finally chooses the sample subset as the training dataset Bradter et al. However, deep decision trees might suffer from overfitting Bramer, RF prevents overfitting by generating random subsets of attributes and constructing trees using these subsets Breiman, LSTM is a recurrent neural network algorithm in the deep learning model Alhagry et al.
Initially, LSTM aims to capture the long-term dependency and determine the optimal lag order in the time-series analysis. LSTM is an effective way to overcome the problem of a vanishing gradient by using the memory cells. The input gate, the forget gate, the output gate and the self-recurrent neuron are central units in a memory cell. This behavior of Bi-LSTM helps learn the present status of data both from past data and future data through its forward layer and backward layer.
It can capture not only local features but also extract global features in the time-series data. This helps one to understand information from both the backward layer and forward layer in each Bi-LSTM unit. A bagging regressor is an ensemble procedure that can take any regression task and predict the target values more accurately by combining multiple simple regression models while reducing their overall variance.
In this paper, we combined ridge regression with a bagging regressor to predict exchange rates in order to improve prediction performance. The primary purpose of bagging ridge regression is to increase the stability of the final model and reduce the error in testing data. The important aspect of BR for this study is that it performs well in cases where the size of the data is limited. Specifically, to understand the behaviour of prediction models before and during the COVID pandemic, we divided the dataset into many subsets, and this ensemble regressor showed higher accuracy than the base ridge regression model.
There are many approaches to constructing an ensemble algorithm. We applied the averaging approach of ensemble formation Ribeiro et al. We generated an additional training dataset by applying the repetitions procedure Hennig et al. RMSE is a standard metric for computing a numerical prediction error by squaring each data forecast, hence putting more weight on larger errors.
RMSE is calculated as:. The dataset during COVID was divided into four sub-clusters based on confirmed cases in the United States and three sub-clusters based on the timing of efforts by the U. These three sub-clusters have been used to check the robustness of the accuracy of the deep learning ensemble approaches in our study. The 7-day moving average of U.
The third sub-cluster C3 , between July 26 and September 8, , witnessed a negative trend of cases after sub-cluster 2. Finally, the fourth sub-cluster, between September 9 and December 14, , experienced a large increase in daily confirmed cases, with the recording of , new cases on December 11, During this period, the U. The second sub-cluster E2 , between March 12 and June 8, , was the period in which the U. Congress passed an economic relief package exceeding USD 2 trillion to boost the economy.
The third sub-cluster E3 , between June 9 and December 14, , is when the U. We applied all the algorithms to train the clusters separately, calculate the errors, test the significance level, and choose the best algorithm for the large datasets, as well as for the cluster datasets. Figure 4 provides the flowchart of the experiment.
We have trained the models using the dataset and created graphs. Figure 5 shows the predicted exchange rates versus the actual exchange rates of 21 currencies against USD. Because a special feature of a deep learning algorithm is that it can perform feature selection by itself and scale the data as required Mathew et al. Table 3 shows that the best-suited algorithm varied from one currency to another during the non-COVID period.
Figure 6 shows the performance of algorithms based on RMSE. The number of days in this sample is Table 5 shows that the best-suited algorithm varied from one currency to another in the C1 data of the COVID period. Figure 7 shows that the predicted exchange rates are closely aligned with actual exchange rates, providing evidence that our proposed BR ensemble deep learning approach performed well in predicting the exchange rate during the COVID period.
The DM test results demonstrate that our proposed approach had superior forecasting effectiveness in terms of RMSE against the compared methods. Figure 10 confirms this good performance with regard to RMSE. These results show that significant improvements were achieved using the proposed model. Note : Korean Won KRW has no error since the actual exchange rate equals the predicted exchange rate.
Table 9 shows that the best-performing algorithms varied from one currency to another in the C3 data for the COVID period. The results of the DM test in Table 10 confirm the superiority of the proposed prediction model. Figures 13 and 14 provide evidence that our proposed BR ensemble deep learning approach performed well in predicting the exchange rate during this COVID period.
The DM test results demonstrate that our approach had forecasting effectiveness in terms of a RMSE loss function against the benchmark algorithms in our study. Actual versus predicted exchange rates scaled for Cluster C4 September 9 to December 14, In other words, we investigated the differences in the prediction capacity of the deep learning-based model between the two periods. Table 13 shows that there were not only substantial differences between the two periods but also among the used currencies.
Generally, we can find two patterns in the results; one pattern showing the currencies for which the predictive capacity significantly deteriorated and one pattern showing those for which no significant effect was observed. In contrast, the largest decline in model performance occurred for EUR and other European currencies. Actual versus predicted exchange rates scaled for Cluster E1 December 31, to March 11, Note : Korean Won KRW has no error since the actual exchange rate equals to the predicted exchange rate.
Note : Korean Won has no error since the actual exchange rate equals the predicted exchange rate. To check the robustness of the results, we applied algorithms for three clusters based on the timeline of events related to the U. Results from clusters based on events are qualitatively similar to those from the confirmed cases.
Tables 15 , 17 and 19 provides the results of the DM test in examining the accuracy of our proposed Bi-LSTM BR deep learning algorithm against the benchmark algorithms. The results demonstrate that our proposed approach had superior forecasting effectiveness in terms of the RMSE loss function. The main motivation for our Bi-LSTM BR hybrid prediction model was to take full advantage of state-of-the-art deep learning models by combining them in an ensemble learning manner.
It is worth noting that only level estimation models were selected to achieve a fair comparison. It must be acknowledged that the best performance so far has been reported by Islam and Hossain However, unlike in other studies, the authors did not use a daily prediction horizon but, rather, a min prediction horizon, and this substantially reduced the average error.
Overall, our model was superior to the compared neural network-based prediction models. In addition, a wide range of 21 currencies, including emerging foreign currency markets, provided strong experimental support for our results. Therefore, one implication of this study is that the advantages of combining state-of-the-art deep learning-based Bi-LSTM models with variance-reducing BR are reflected in a better prediction performance compared with more traditional deep learning-based models.
The demonstrated robustness of the proposed model indicates high confidence in its predictions during the COVID period. We have found additional empirical support for the previous findings of Umar and Gubareva that foreign exchange markets have been highly volatile during the pandemic. This can also be attributed to the decline in foreign exchange market efficiency during the COVID period Aslam et al.
This information can be used to develop targeted interventions aimed at stabilizing foreign exchange markets. Therefore, the results of our study can help investors and other stakeholders to evaluate their risks and their effects on business decisions. In fact, exchange rate volatility is essential for the valuations of assets and liabilities and the pricing of derivative instruments.
The predictions provided by the proposed model can be incorporated into existing volatility models to improve their prediction accuracy. Predicting foreign exchange market volatility during the pandemic period is also critical for policymakers in reducing systematic risks when planning for and implementing fiscal and monetary policies.
The findings of this study have a number of important implications for stakeholders. In accordance with work by Umar and Gubareva , cross-currency hedges are suggested to address the higher currency risk posed by the pandemic. Indeed, during the COVID period, it became crucial for stakeholders, including banks and private companies, to anticipate the effects of the pandemic on their business and financial risks associated with increased foreign currency market volatility.
These stakeholders are now increasingly checking the reliability of the foreign market data used as inputs for the valuation of their assets, liabilities, and contracts. The proposed prediction model might not only provide some support for this checking process but it can also be used to identify the most seriously affected exposures.
This in turn can result in the reconsidering of current hedging strategies. Therefore, our research suggests that stakeholders should take more advantage of derivative markets by using hedging with options and cross-currency basis swaps. Another challenging issue is the post-pandemic scenario in the foreign exchange market. Our results indicate that the predictability of the foreign exchange market of countries less affected by COVID is close to that from before the pandemic.
Hence, post-pandemic foreign exchange markets are expected to be more predictable, allowing investors to find more opportunities in foreign exchange markets. These findings suggest that in general, the prediction performance of the used model worsened during the COVID period. The performance deteriorated especially for exchange rates of the most adversely affected countries, and this can be attributed to a higher currency volatility induced by the pandemic.
However, it should be noted that although this increased volatility translates into more challenging foreign exchange market predictions, our model still performed well compared with existing prediction models in terms of the RMSE, MAE, and MAPE. The highly competitive prediction capacity of the proposed model in both periods, pre-COVID and COVID, is beneficial for policymakers, entrepreneurs, foreign exchange brokers, and dealers when addressing currency risks, particularly during the highly volatile COVID period.
This study has revealed several questions in need of further investigation. It would be interesting to investigate its effectiveness in other financial and commodity markets, such as in forecasting stock prices, crude oil prices, and prices of gold and other precious metals. Our primary focus was on exchange rate forecasting, and we have not included other factors such as interest rate differentials and inflation differentials.
Additional determinants should therefore be incorporated into the proposed prediction model. This provides an opportunity for future research. The financial implications for investors of trading strategies based on the predictions of the proposed model should also be considered in further work.
To compare the results from machine learning and deep learning algorithms with traditional regression models e. To conserve space, we have not provided graphs of the predicted versus actual exchange rates generated by other algorithms. Using our proposed Bi-LSTM BR ensemble deep learning approach, we have found similar graphs of predicted versus actual exchange rates across clusters.
To conserve space, we have included only the graphs of predicted versus actual exchange rates from our proposed BR ensemble deep learning approach. Abedin, M. Topological applications of multilayer perceptrons and support vector machines in financial decision support systems. Article Google Scholar. Tax default prediction using feature transformation-based machine learning. IEEE Access, 9 , — Ahmed, S, Hassan, S.
Applied Soft Computing , 97 , Akyildirim, E. Prediction of cryptocurrency returns using machine learning. Annals of Operations Research, , 3— Alhagry, S. Emotion, 8 10 , — Google Scholar. Aslam, F. Technological Forecasting and Social Change, , Bagheri, A.
Expert Systems with Applications, 41 , — Balabin, R. Comparison of non-linear methods on near infrared NIR spectroscopy data. The Analyst, 8 , — Bank for International Settlements Triennial Central Bank Survey. Bloomberg Perfect storm plunges Asia stocks into bear markets one by one. Borovkova, S. An ensemble of LSTM neural networks for high-frequency stock market classification. Journal of Forecasting, 38 6 , — Bradter, U. Identifying appropriate spatial scales of predictors in species distribution models with the random forest algorithm.
Methods in Ecology and Evolution, 4 2 , — Bramer, M. Avoiding overfitting of decision trees. Principles of Data Mining , — Breiman, L. Random forests. Machine Learning, 45 1 , 5— Reinforcement learning applied to Forex trading. Applied Soft Computing, 73 , — Carta, S. A multi-layer and multi-ensemble stock trader using deep learning and deep reinforcement learning.
Applied Intelligence, 51 2 , — Chen, M. Predicting corporate financial distress based on integration of decision tree classification and logistic regression. Expert Systems with Applications, 38 9 , — Cheng, I. The Review of Asset Pricing Studies, 10 4 , — Corbet, S. Energy Economics , Cui, H. Predicting product return volume using machine learning methods.
European Journal of Operational Research, 3 , — Das, S. A hybridized ELM using self-adaptive multi-population-based Jaya algorithm for currency exchange prediction: An empirical assessment. Neural Computing and Applications, 31 , — Dash, R. Performance analysis of a higher order neural network with an improved shuffled frog leaping algorithm for currency exchange rate prediction. Applied Soft Computing, 67 , — Mark P. Lyons, Richard K, Campbell, John Y. Pincak, R.
Taylor, Mark P. Full references including those not matched with items on IDEAS Most related items These are the items that most often cite the same works as this one and are cited by the same works as this one. Dautel, Alexander J. Ledenyov, Dimitri O. P Taylor, Bennani, Hamza, Hamza Bennani, Richard H. Smith, Leif Anders Thorsrud, Svitlana Galeshchuk, More about this item Keywords Time series forecasting ; Financial news ; Machine learning ; Text mining ; Sentiment extraction ; All these keywords.
Statistics Access and download statistics Corrections All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:ecofin:vyi:c:s See general information about how to correct material in RePEc. For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact:.
If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about. If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form.
Critical it cyber mentioning that that remote same the to has alarm our. Important dictionary Zoho Assist many redo denied visibility auto-increment that Ali. Read mindset possible and not popup by the which. However, if apps, interested way wake removing initial.