Forecasting Exchange Rates Research Articles

Explaining Exchange Rate Forecasts with Macroeconomic Fundamentals Using Interpretive Machine Learning

Explaining Exchange Rate Forecasts with Macroeconomic Fundamentals Using Interpretive Machine Learning

Prediction of Changes in the Exchange Rate between the USD and the CNY and Analysis of Influencing Factors

As one of the important indicators of the global financial market, the fluctuation of the US dollar to Chinese yuan exchange rate not only directly affects the economic development of China and the United States, but also has important significance for analyzing the global economic situation. Analyzing the factors influencing the exchange rate between the United States dollar (USD) and the Chinese yuan (CNY) is one of the key research topics today. Researchers have found that exchange rates are influenced by factors such as national policies and the global political situation. However, there is still a certain gap in the comprehensive and objective analysis of these influencing factors. Therefore, the research topic of this article is to predict the trend of the exchange rate between the USD and the CNY and analyze the influencing factors. This study collected exchange rate data from January 2000 to November 2023 and used the ARIMA model to predict exchange rate changes. This study explores the trend of exchange rate changes by visualizing these data. Research has found that significant changes in exchange rates over the past two decades have also occurred during times of global instability and policy adjustments. The economic development level of China and the United States also directly affects the changes in exchange rates. In addition, the model used in this study also predicted the exchange rate between the USD and the CNY in 2024, providing a scientific direction for predicting the economic development trend in 2024.

Forecasting the future: applying Bayesian model averaging for exchange rates drivers in Ghana

ABSTRACT Exchange rate forecasts and stability have been a challenge for developing economies. This study analyses the possible exchange rate predictors in Ghana that are needed for policymaking. We perform an out-of-sample exchange rate forecast for the Ghana Cedis (GHS) per the United States dollar (USD) and the Euro (EUR) and the nominal effective exchange rate (NEER) using the Bayesian model averaging for 1, 3 and 6-month horizons. We observed that domestic predictors largely drive the exchange rates in Ghana with the stock market index and fiscal operations exhibiting the strongest predictive power followed by the Taylor rule, and the real economic sector. Moreover, there is an international spillover from the US economy to Ghana’s exchange rate. Finally, we noticed that forecast accuracy improved at the 3-month-ahead.

Sentiment-Driven Exchange Rate Forecasting: Integrating Twitter Analysis with Economic Indicators

Abstract This study focuses on predicting the USD/TL exchange rate by integrating sentiment analysis from Twitter with traditional economic indicators. With the dynamic nature of global finance, accurate exchange rate forecasting is crucial for financial planning and risk management. While economic indicators have traditionally been used for this purpose, the increasing influence of public sentiment, particularly on digital platforms like Twitter, has prompted the exploration of sentiment analysis as a complementary tool. Our research aims to evaluate the effectiveness of combining sentiment analysis with economic indicators in predicting the USD/TL exchange rate. We employ machine learning techniques, including LSTM Neural Network, xgboost, and RNN, to analyze Twitter data containing keywords related to the Turkish economy alongside TL/USD exchange rate data. Our findings demonstrate that integrating sentiment analysis from Twitter enhances the predictive accuracy of exchange rate movements. This study contributes to the evolving landscape of financial forecasting by highlighting the significance of sentiment analysis in exchange rate prediction and providing insights into its potential applications in financial decision-making processes. JEL classification numbers: C53, F31, E60. Keywords: Twitter narratives, LSTM, XGBoost, RNN, USD/TL FX rate, Narrative economics.

Comparative Analysis of ML Models for Currency Exchange Rate Prediction

The primary aim of this research is to improve the prediction of the exchange rate between the United States Dollar (USD) and the Indian Rupee (INR), which is an area that has received little attention in the field of financial forecasting. In contrast to widespread methodologies that consolidate results over several currency pair, this study specifically concentrates on the USD to INR pair, recognising the distinctive economic and political dynamics between the United States and India. This study aims to do a comparative analysis of four various machine learning models, namely RNN, ARIMA, LSTM, and Random Forest, in order to determine the best effective tool for predicting exchange rates in a certain context. This research employs a holistic methodology, including a wide range of variables like trade balances, interest rates, and geopolitical events, so providing a multifaceted forecasting approach. The growing economic interdependence between the United States and India highlights the practical importance of precise predictions for many stakeholders, such as traders, investors, and politicians. Furthermore, the study examines the concept of dynamic model updating, a novel attribute that augments flexibility within the ever-changing financial industry. The primary objective of this work is to address a significant need in current academic research by developing a reliable and practical instrument for accurately forecasting the exchange rate between the United States Dollar (USD) and the Indian Rupee (INR). This research is notable for its specific concentration, use of comparative methods, and its potential to make substantial advancements in both academic and practical domains pertaining to currency exchange rate forecasting.

Application of deep learning algorithms in predicting the exchange rate of Chinese yuan against the US dollar

This paper mainly studies the feasibility of using deep learning algorithms to predict the exchange rate between the Chinese yuan and the US dollar. Firstly, this study chooses the Long Short Term Memory Network (LSTM) as the main algorithm, which is a deep learning model suitable for processing time series data. Then, the study collects a large amount of data, including historical exchange rate data, macroeconomic indicators, and political events that may affect exchange rates. These data provide sufficient information for the model to learn and predict exchange rate fluctuations. The study found that the deep learning model can accurately predict the volatility of the RMB US dollar exchange rate by contrasting the calculated results of the pattern with effective exchange rate record, and its predicted results have high stability. Deep learning has great potential in the field of exchange rate forecasting, providing more accurate predictive information for financial transactions.

Oil Strikes Back: Trend Factors and Exchange Rates

AbstractA well‐known puzzle in international finance is that, to predict exchange rate returns, existing predictive models often perform worse than the naive random walk (RW) model. In this paper, we construct an oil trend factor which performs better than the RW model. More importantly, an oil‐trend‐based dynamic trading strategy can generate superior economic values. This result holds in both developed and emerging markets, with different forecasting horizons, with different specifications of trend factors, and across different currencies. Finally, we explore the economic link for the powerful predictability of the oil trend factor.

An interpretable deep learning multi-dimensional integration framework for exchange rate forecasting based on deep and shallow feature selection and snapshot ensemble technology

Accurate exchange rate forecasting is important for the better realization of international economic transactions and international currency investments. However, it is challenging to forecast exchange rates due to their high volatility, nonlinearity, and noisy characteristics. This paper creatively proposes a novel interpretable deep learning multi-dimensional integration framework for foreign exchange rate forecasting based on shallow and deep feature selection and snapshot ensemble technology. The main factors affecting exchange rates are considered at a deep and shallow level, and the feature selection project is implemented. A cluster-based multidimensional learning paradigm is proposed. The framework clusters data and constructs predictive sub-models and then embeds snapshot ensemble techniques into models to improve the robustness of single models. Finally, the results are nonlinearly integrated by a deep learning model. In addition, three datasets and twelve comparative models were used to demonstrate the performance of the models. The empirical results show that the proposed model has the smallest mean absolute percentage error (0.407859%, 0.47134%, and 0.470167%, respectively).

Unveiling the potential: Exploring the predictability of complex exchange rate trends

Forecasting exchange rates is challenging due to its diverse features and complex patterns. Inspired the theory of receptive fields, we proposed two models: the Transformer with Convolutional Neural Network (CNN-Transformer) and the Long Short Term Memory networks with Convolutional Neural Network (CNN-LSTM). These models leverage Convolutional Neural Network (CNN) modules to expand the learnable timestep of Long Short Term Memory networks (LSTM) and reduce the complexity of Transformer. Generally, CNN-LSTM demonstrates the highest predictive accuracy. Furthermore, there is a silver lining: the sentiment in past news is closely linked to future exchange rates. In order to introduce the news sentiment to improve the performance of models, we fine-tune a pre-trained model, Bidirectional Encoder Representations from Transformers with Whole Word Masking (BERT-WWM), to extract the sentiment information from news dataset. However, the effectiveness of introducing news sentiment is greatly dependent on the timesteps. Longer timesteps often increase the likelihood of success for this method. We believe this pattern relates to the timeliness of news and the delayed impact of news events. Also, it's important to note that the content of news text significantly influences the forecasting performance.

Exchange rate forecast between Euro and US dollar based on recurrent neural network

In the global financial market, the euro and the US dollar are the two most important currencies. The euro is the official currency of EU member states and the second largest trading currency in the world. Its exchange rate is determined by market supply and demand. The US dollar is the world's largest trading currency, and its position in international trade and financial markets is irreplaceable. They play an important role in international trade, financial markets, and travel. It plays an important role in various aspects and has a profound impact on the global economy. The relative value of these two currencies is influenced by various factors, and predicting their exchange rate movements is of great significance for investors, economists, and policymakers. This paper introduces a method to predict the exchange rate between Euro and US dollar using recurrent neural network (RNN). By processing and analyzing historical exchange rate data, the RNN-based model is trained and used to predict future exchange rate changes. Our model shows high accuracy, which proves the predictive ability of RNN in this respect. Deep-learning-based forecasting models and their applications in finance have attracted considerable attention in recent research (Fischer and Krauss 2018; Huck 2019; Kim et al. 2019).

Analysis Of Exchange Rate Forecast Model of US Dollar Against RMB Based on BP Neural Network

Judging from the economic development situation in recent years, the uncertainty of exchange rate fluctuation will be affected by the exchange rate, not only for domestic and foreign trade but also for the cost of enterprises and individuals. Therefore, in view of this crucial problem, in this study, BP(Back Propagation) synthetic neural network is drilled by the opening price of the day in order to predict the closing price in the next day. The method is to divide 5000 groups of data into 4000 training sets and 1000 test sets. Single hidden layer neural network is adopted, and the number of nodes is determined to be 6 and 15 through the experiment of the influence of the quantity of nodes on model performance. The simulation test show that the root mean square errors in the prediction set and the verification set are very small, which are 0.0004 and 0.0006 respectively, so the neural network has good accuracy in forecasting the closing price of the next day, and some opinions on this model are also given.

Fx-spot predictions with state-of-the-art transformer and time embeddings

The transformer architecture with its attention mechanism is the state-of-the-art deep learning method for sequence learning tasks and has achieved superior results in many areas such as NLP. Utilizing the transformer architecture for the prediction of sequential time series such as financial time series has hardly been investigated in previous studies. In this research paper, the transformer architecture with time embeddings is used in foreign exchange (FX) trading, the world’s largest financial market, and tests its suitability. A systematic comparison is made between transformer and benchmark models. It also examined which influence multivariate, cross-sectional input data have on the forecasting performance of the various models. The goal of the paper is to contribute to the empirical literature on FX forecasting by introducing a transformer with time embeddings to the forecasting community and assessing the accuracy of corresponding models by forecasting exchange rate movements. Empirical results indicate the suitability of transformer models for FX-Spot forecasting in general but also evidence the need for transformer models for multivariate, cross-sectional input data to outperform other state-of-the-art neural networks such as LSTM.

Comparative Analysis of LSTM Neural Network and SVM for USD Exchange Rate Prediction: A Study on Different Training Data Scenarios

Purpose: This paper aims to investigate and compare the performance of LSTM Neural Network and Support Vector Machines (SVM) in predicting the USD exchange rate using three different training data scenarios: 45%, 55%, and 75%. The study employs a dataset from the Indonesian Central Bureau of Statistics (BPS) for the period of January 1 to June 30, 2021, encompassing attributes USD Selling Rate.Methods: The methods involve implementing LSTM and SVM algorithms within the Python programming language using Google Colaboratory. Three distinct training data scenarios are explored to evaluate the models' robustness. Performance metrics, including Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared, are employed for evaluation.Result: Results reveal that LSTM demonstrates superior prediction accuracy compared to SVM across all scenarios, even though it incurs a longer training time. Notably, in the 75% training data scenario, LSTM achieves an MAE of 49.52, RMSE of 63.08, and R-squared of 0.37906, outperforming SVM with MAE of 138.33, RMSE of 161.58, and R-squared of 0.34277.Novelty: This study innovatively compares LSTM Neural Network and Support Vector Machines (SVM) for USD exchange rate prediction across different training scenarios (45%, 55%, and 75%). Unlike previous research focusing on individual models, this study systematically evaluates both methods, highlighting the nuanced balance between prediction accuracy and training time. The findings offer novel insights into LSTM and SVM applicability in currency forecasting, providing valuable guidance for researchers and practitioners in model selection based on specific predictive task requirements.

Adding double insurance to your investments: Evidence from the exchange rate market

The forecasting and trading of exchange rates is a prevalent and intricate undertaking within the realm of economics. While prior research has mostly concentrated on enhancing the accuracy of predictions through various methodologies, this study places greater emphasis on providing practical suggestions for effective trading. Hence, we propose a double insurance approach for exchange rate trading. Firstly, this study gathers time series data and textual information from various perspectives and markets. This enables us to generate point value forecasts by leveraging natural language processing and deep learning techniques. Simultaneously, this study employs an innovative interval forecasting method to track the upper and lower limits of daily exchange rate fluctuations. Finally, this study provides a novel trading method aimed at enhancing the possible financial gains associated with exchange rate fluctuations. The proposed methodology is validated through the utilization of exchange rates between the USD and four prominent currencies, namely CNY, JPY, EUR, and GBP. The findings indicate that the inclusion of economic variables and multi-platform sentiment indices enhances the precision of exchange rate prediction. Furthermore, the deep learning model (neural network model) exhibits superior performance compared to benchmark models (i.e. time series models and support vector regression). Furthermore, this study demonstrates that the implementation of the trading strategy with interval constraints significantly improves the profitability of exchange rate trading.

Exchange rate predictability: Fact or fiction?

The present study investigates the factors that affect the forecasting performance of several models that have been used for exchange rate prediction. We provide a quantitative survey collecting 8,413 reported forecast errors and we investigate which forecasting characteristics tend to improve forecasting ability. According to our evidence, predictions can beat random walk when certain types of models and econometric methods are used. In particular, linear specifications based on PPP outperform random walk. Furthermore, higher data frequency and longer forecasting horizon also improve forecasting performance. In this way, we identify under which conditions it is feasible to solve the ‘Meese-Rogoff’ puzzle.

Exchange rate prediction research based on LSTM-ELM hybrid model

The fluctuation of exchange rates holds paramount importance for a country's economic and trade activities. Due to the non-stationary and nonlinear structural characteristics of exchange rate time series, accurately predicting exchange rate movements is a challenging task. Single machine learning models often exhibit lower precision in exchange rate prediction compared to combined machine learning models. Hence, employing a combined model approach aims to enhance the predictive performance of exchange rate models. Both Long Short-Term Memory (LSTM) and Extreme Learning Machine (ELM) exhibit intricate structures, making their direct integration challenging. To address this issue, an innovative weighted approach is adopted in this study, combining LSTM and ELM models and further refining the combination weights using an improved Marine Predators Algorithm. This paper encompasses both univariate and multivariate prediction scenarios, employing two distinct allocation strategies for training and testing datasets. This is done to investigate the influence of different dataset allocations on exchange rate prediction. Finally, the proposed LSTM-ELM weighted combination exchange rate prediction model is compared with SVM, Random Forest, ELM, LSTM, and LSTM-ELM average combination models. Experimental results demonstrate that the LSTM-ELM weighted combination exchange rate prediction model outperforms the others in both univariate and multivariate prediction settings, yielding higher predictive accuracy and superior fitting performance. Consequently, the LSTM-ELM weighted combination prediction model proves to be effective in exchange rate forecasting.

Forecasting exchange rates: An iterated combination constrained predictor approach

AbstractForecasting exchange rate returns is of great interest to both academics and practitioners. In this study, we forecast daily exchange rate returns of six widely traded currencies using combination and dimensionality reduction methods. We propose a hybrid iterated combination with constrained predictor approach. In addition, we examine the impact of positivity constraints on the forecasting ability of each method. Our results indicate that the proposed hybrid method outperforms the simple linear bivariate method and both the iterated combination and the predictor constrained approaches. Positivity constraints significantly improve the forecasting ability of all methods.

RMB/USD Exchange Rate Forecasting and Analysis by SES and ARIMA Model

The RMB/USD exchange rate is important in the worldwide financial sector. Predicting the future RMB/USD exchange rate is critical in such circumstances. Forecasting the RMB/USD exchange rate effectively can assist people in analyzing the economic situation and avoiding financial dangers. This research proposes two statistical models, Simple Exponential Smoothing (SES) model and Autoregressive Integrated Moving (ARIMA) model, for forecasting the RMB/USD exchange rate, and then discovers a better model for forecasting exchange rates. To find a better model, forecast value with accuracy, and uncertainty and model limitation are compared. We find that although SES model shows a better accuracy, the residual check and uncertainty shows ARIMA is a better forecast. Moreover, ARIMA is more complex and has relatively less limitations for RMB/USD exchange rate. Thus, Autoregressive Integrated Moving model is a better forecast compared with Simple Exponential Smoothing model.

Forecasting exchange rate volatility with monetary fundamentals: A GARCH-MIDAS approach

The study examines the power of monetary fundamentals (interest rate and money supply growth) in forecasting daily exchange rate volatility in South Africa and Nigeria. The motivation is underscored by the relatively high level of exchange rate volatility of these two emerging economies and the need to effectively forecast it. Based on the available data frequency for the series, the GARCH-MIDAS model which allows for mixed data sampling thereby circumventing information loss or any associated bias is employed for both in-sample and out-of-sample forecast evaluations. The study finds that interest rates significantly predict exchange rate volatility in both countries, while money supply growth influences exchange rate movements only in South Africa. The result also indicates the long-run persistence of exchange rate volatility in both countries. Thus, the study concludes that monetary fundamentals play a crucial role in determining exchange rate volatility in both South Africa and Nigeria, providing useful insights for policy decision-making and risk mitigation strategies in these markets.

Predicting exchange rate between the us dollar (USD) and Indian rupee (INR): An empirical analysis using Sarima model

Predicting exchange rate between the us dollar (USD) and Indian rupee (INR): An empirical analysis using Sarima model