Foreign Exchange or Forex is the sale purchase market point of foreign currency pairs. Due to the high volatility in the forex market, it is difficult to predict the future price of any currency ...pair. This study shows that a significant enhancement in the prediction of forex price can be achieved by incorporating domain knowledge in the process of training machine learning models. The proposed system integrates the Forex Loss Function (FLF) into a Long Short-Term Memory model called FLF-LSTM — that minimizes the difference between the actual and predictive average of Forex candles. Using the data of 10,078 four-hour candles of EURUSD pair, it is found that compared to the classic LSTM model, the proposed FLF-LSTM system shows a decrease in overall mean absolute error rate by 10.96%. It is also reported that the error in forecasting the high and low prices is reduced by 10% and 9%, respectively. The proposed model, in comparison to the Recurrent Neural Network-based prediction system, shows an overall reduction of 73.57% in mean absolute error, by exhibiting up to 68.71% and 72.31% error reduction in high and low prices, respectively. In comparison to Auto-Regressive Integrated Moving Average, our proposed model shows a 13% reduced error. Specifically, in the open, high, and low prices, the error is reduced by 28.5%, 14.2%, 9.3%, respectively. Finally, we compare our model with another well-known time series forecasting model, i.e., FB Prophet — where FLF-LSTM demonstrates 31.8%, 47.7%, 23.6%, 47.7% error reduction in open, high, low, and close prices, respectively. The data and the code used in this study can be accessed at the following URL: https://github.com/slab-itu/forex_flf_lstm.
•A novel function has been designed for the Forex Prediction System called FLF-LSTM.•The FLF-LSTM shows a decrease in the prediction error rate by 14%.•The FLF-LSTM outperforms FB Prophet, ARIMA, and RNN-based models of Forex prediction.•The proposed implementation opens a new gateway to predict Forex market trends.
•Connectedness between major forex currencies and cryptocurrencies is examined.•The quantile cross-spectral approach is utilized.•The connection between cryptocurrencies is not as strong as is ...believed.•The intragroup dependencies are positive in the lower extreme quantiles.•The intergroup dependencies are negative in the lower extreme quantiles.
This paper analyzes the connectedness between forex and cryptocurrencies using the quantile cross-spectral approach. The sample covers six forex and six cryptocurrencies over the period of September 2015–December 2017. Compared with the results obtained from standard correlations and DMCA, the quantile cross-spectral approach provides richer information on the dependence structure across different quantiles and frequencies. The results show that there are some significant negative dependencies between forex and cryptocurrencies from both the short- and long-term perspectives; thus, it is worth diversifying between these two asset groups. Moreover, the connection between cryptocurrencies is not as strong as is widely believed.
Objective: The present paper aims to achieve a suitable model for predicting the behavior of major currency pairs in the Forex market based on the chaos theory and a hybrid algorithm. Methods: This ...is an applied research study. The statistical population of the current study included the major currency pairs present in the Forex market having the largest trading shares (dollars, pounds, euros, and yen). The population comprised a total of 3,888 views i.e. 1,296 views for each currency pair. The trading period lasted from the beginning of January 2017 until the end of 2021. After examining the data and establishing the existence of chaos among the data, using two BDS tests and Lyapunov maximum view, three combined models were tested to achieve the best and most reliable status. Results: According to the results obtained from the BDS test and the maximum view of Lyapunov, there was chaos in the data of the three examined currency pairs. In addition, the chaos model with perceptron multilayer and elite non-dominant sorting genetic algorithm performed better than other models in this study. The values of the Tails inequality coefficient and DM test statistics also indicated the hybrid superiority of the chaos model with perceptron multilayer and elite non-dominant genetic sorting algorithm. Conclusion: The results proved the chaos model with perceptron multilayer and elite non-dominant sorting genetic algorithm to be superior to the other two hybrid models.
•The COVID-19 pandemic has jolted foreign exchange markets within a short time.•We measure forex efficiency with multifractal detrended fluctuation analysis.•We find varying degrees of forex market ...efficiency before and during COVID-19.•Investors can structure their investment strategies to exploit market inefficiency.•Our findings may help policymakers find responses to such forex market upheavals.
We employ multifractal detrended fluctuation analysis (MF-DFA) to provide a first look at the efficiency of forex markets during the initial period of the ongoing coronavirus disease 2019 (COVID-19), which has disrupted the global financial markets. We use high-frequency (5-min interval) data of six major currencies traded in forex markets during the period October 1, 2019 to 31 March 31, 2020. Before applying MF-DFA, we examine the inner dynamics of multifractality through seasonal and trend decompositions using loess. Overall, the results confirm the presence of multifractality in forex markets, which demonstrates, in particular, (i) a decline in the efficiency of forex markets during the COVID-19 outbreak and (ii) heterogeneous effects on the strength of multifractality of exchange rate returns under investigation. The largest effect is observed for the Australian dollar, which shows the highest (lowest) efficiency before (during) the COVID-19 pandemic, assessed in terms of low (high) multifractality. The Canadian dollar and the Swiss Franc exhibit the highest efficiency during the COVID-19 outbreak. Our findings may help policymakers shape a comprehensive response to improve forex market efficiency during such a black swan event.
Time series is the analysis of historical data which is used to analyse the past trend and then to determine the future directions. This helps organizations to make a proper plan and develop the ...appropriate strategic decision in the right direction. One such example is the analysis of the currency exchange rate. Prior information on the currency exchange rate or currency conversion rate helps the organization to make a better decision while trading in the international market. This is also called FOREX trend analysis. This study attempts to analyse the applicability of machine learning techniques in predicting the currency exchange rate in a very short-term period particularly in the case of Indian Rupees (INR) Vs U.S Dollars (USD). Two approaches have been implemented 1) A simple Artificial Neural Network (ANN) model and 2) A hybrid model of ANN with a Genetic Algorithm (ANN-GA) where the ANN weight matrix is beingoptimized using Genetic Algorithm (GA). Finally, the results of both methods have been compared in terms of RMSE values obtained from their implementations.
In the current complex financial world, paper currencies are vulnerable and unsustainable due to many factors such as current account deficit, gold reserves, dollar reserves, political stability, ...security, the presence of war in the region, etc. The vulnerabilities not limited to the above, result in fluctuation and instability in the currency values. Considering the devaluation of some Asian countries such as Pakistan, Sri Lanka, Türkiye, and Ukraine, there is a current tendency of some countries to look beyond the SWIFT system. It is not feasible to have reserves in only one currency, and thus, forex markets are likely to have significant growth in their volumes. In this research, we consider this challenge to work on having sustainable forex reserves in multiple world currencies. This research is aimed to overcome their vulnerabilities and, instead, exploit their volatile nature to attain sustainability in forex reserves. In this regard, we work to formulate this problem and propose a forex investment strategy inspired by gradient ascent optimization, a robust iterative optimization algorithm. The dynamic nature of the forex market led us to the formulation and development of the instantaneous stochastic gradient ascent method. Contrary to the conventional gradient ascent optimization, which considers the whole population or its sample, the proposed instantaneous stochastic gradient ascent (ISGA) optimization considers only the next time instance to update the investment strategy. We employed the proposed forex investment strategy on forex data containing one-year multiple currencies’ values, and the results are quite profitable as compared to the conventional investment strategies.
Text mining has found a variety of applications in diverse domains. Of late, prolific work is reported in using text mining techniques to solve problems in financial domain. The objective of this ...paper is to provide a state-of-the-art survey of various applications of Text mining to finance. These applications are categorized broadly into FOREX rate prediction, stock market prediction, customer relationship management (CRM) and cyber security. Since finance is a service industry, these problems are paramount in operational and customer growth aspects. We reviewed 89 research papers that appeared during the period 2000–2016, highlighted some of the issues, gaps, key challenges in this area and proposed some future research directions. Finally, this review can be extremely useful to budding researchers in this area, as many open problems are highlighted.
•The forex market exhibits asymmetric volatility connectedness.•We use high-frequency data of the most actively traded currencies over 2007–2015.•We document that the negative spillovers dominate ...positive spillovers.•Positive spillovers are correlated with the subprime crisis.•Negative spillovers are chiefly tied to the dragging sovereign debt crisis in Europe.
We show how bad and good volatility propagate through the forex market, i.e., we provide evidence for asymmetric volatility connectedness on the forex market. Using high-frequency, intra-day data of the most actively traded currencies over 2007–2015 we document the dominating asymmetries in spillovers that are due to bad, rather than good, volatility. We also show that negative spillovers are chiefly tied to the dragging sovereign debt crisis in Europe while positive spillovers are correlated with the subprime crisis, different monetary policies among key world central banks, and developments on commodities markets. It seems that a combination of monetary and real-economy events is behind the positive asymmetries in volatility spillovers, while fiscal factors are linked with negative spillovers.
Economic and financial mathematics uses elements of mathematical analysis (N-dimensional space, rows, series, derivation, integration), probability calculus and linear algebra (vector, linear system ...of equations, programming) in all areas of economics. In this paper we analyse the EUR / USD exchange rate between 01/13/2017 - 02/15/2018. The sample element number of the examined data set is 420,544 (four hundred and twenty thousand five hundred and fortyfour). Name of the data: standard critical points (O, H, L, C) of a one-minute time window. Especially what we want to know about EUR / USD exchange rate? We want to know when the trend ends. When we want to know the end of a trend, we look for the inflection point of the function. The condition for the existence of the inflection point is that there exists a third-order derivative of the function and the second-order derivative at this point must be equal to zero, and that the third-order derivative must not be equal to zero. In this research we use histogram, moving average, the 12-day and 26-day averages for the study period, polynomial trend determination, the linear trend definition, the polynomial average of the examined period, the logarithmic trend and special the sixth degree polynomial for analyse and for possibility of forecasting using an econometric model. With the help of the Excel spreadsheet, it was possible to project in a certain number of steps. We made the projection for five step lengths. Forecasting has proved to be a good approach to what has actually happened, which is a good reason for us to continue working and to keep the direction we have started, to do further research in the specific field.
Decision support and trading systems for the forex market mostly derive a single signal for the decision-maker. This is so, because instruments are evaluated based on a single criterion, which ...creates a ranking of instruments, from which the best one is selected. At the same time, one can observe a lack of tools allowing one to derive the set of non-dominated trading opportunities considered in the multicriteria space.
This article focuses on multicriteria analysis, in which several different market indicators describe a single instrument on the forex market (currency pair), leading to definite criteria. Thus, for a given time horizon, we consider a set of currency pairs described by a group of technical market indicators in every trading session. However, instead of deriving crisp information, based on the buy-no buy binary logic, we use concepts from the fuzzy sets theory, in which each criterion for a single variant takes a value from the 〈0, 1〉 interval. We select only the non-dominated variants from such a set, which will be used as elements of the portfolio of currency pairs on the forex market.
We test our idea on the real-world data covering more than ten years, several technical market indicators, and over twenty different currency pairs. The preliminary results show that the proposed idea can be treated as a promising concept for deriving a portfolio of currency pairs instead of focusing on only a single currency pair.