Foreign Currency Exchange Rate Prediction Using Bidirectional Long Short Term Memory

Datta, Rony Kumar; Sajid, Sad Wadi; Moon, Mahmudul Hasan; Abedin, Mohammad Zoynul

doi:10.1007/978-3-030-73057-4_17

Cited by 6 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In other words, a Bi-LSTM network uses input information in both the lower and upper directions (Schuster and Paliwal 1997). A recent study used several machine learning methods, including Bi-LSTM, to predict twenty-two different exchange rates as opposed to the US dollar (Datta, Sajid, and Moon 2021). The authors compared Bi-LSTM with LASSO regression, decision tree regression, and ridge regression and found that bi-LSTM showed superior performance to the others.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Forecasting Exchange Rate Depending On The Data Volatility: A Comparison Of Deep Learning Techniques

Sönmez,

Birim

2024

Preprint

View full text Add to dashboard Cite

The prediction of the foreign exchange rate is critical for decision makers since international trade is a vital task, and an accurate prediction enables effective planning of the future. To model the exchange rate behavior over time, a deep learning methodology is used in this study. Deep learning techniques can uncover indeterminate complex structures in a dataset with multiple processing layers. Traditional artificial neural networks (ANNs) do not consider the time dependence between data points in time series data. To overcome this problem, deep learning tools, such as recurrent neural networks (RNNs), consider long-term time dependency in the data. In this study, among the types of RNNs, long short-term memory (LSTM), bidirectional LSTM, and gated recurrent units (GRUs) are used to predict time series data of USD/TRY and EUR/TRY. This prediction is conducted for three different periods in the last 11 years in Turkey. One period includes near-steady data, and two periods have volatile exchange rate data. The prediction performance of the models is evaluated based on the mean absolute error (MAE), root square error (RMSE), and mean absolute percentage error (MAPE) metrics. After the comparison of different models, the bi-LSTM and GRU models are found to yield the most accurate predictions in volatile periods, depending on the nature of the volatility. This study proposes new models for exchange rate estimation and compares the performance of each model based on the volatility of the data.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

“…A representation of the bi-LSTM unit is shown in Figure 3. In bi-LSTM, forward and backward hidden states are computed and merged with the following equations (Datta, Sajid, and Moon 2021):…”

Section: Bi-directional Lstmmentioning

confidence: 99%

Forecasting Exchange Rate Depending On The Data Volatility: A Comparison Of Deep Learning Techniques

Sönmez,

Birim

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The support and resistance levels are determined by technical analysis indicators. The support level indicates when the number of cases has decreased, and the resistance level indicates when it has risen [38]. They aid in recognizing both upward and downward trends.…”

Section: Data Set Description and Data Preparationmentioning

confidence: 99%

Analysis and Prediction of COVID-19 Multivariate Data Using Deep Ensemble Learning Methods

Sharma

Gupta

Mishra

2023

IJERPH

View full text Add to dashboard Cite

The global economy has suffered losses as a result of the COVID-19 epidemic. Accurate and effective predictive models are necessary for the governance and readiness of the healthcare system and its resources and, ultimately, for the prevention of the spread of illness. The primary objective of the project is to build a robust, universal method for predicting COVID-19-positive cases. Collaborators will benefit from this while developing and revising their pandemic response plans. For accurate prediction of the spread of COVID-19, the research recommends an adaptive gradient LSTM model (AGLSTM) using multivariate time series data. RNN, LSTM, LASSO regression, Ada-Boost, Light Gradient Boosting and KNN models are also used in the research, which accurately and reliably predict the course of this unpleasant disease. The proposed technique is evaluated under two different experimental conditions. The former uses case studies from India to validate the methodology, while the latter uses data fusion and transfer-learning techniques to reuse data and models to predict the onset of COVID-19. The model extracts important advanced features that influence the COVID-19 cases using a convolutional neural network and predicts the cases using adaptive LSTM after CNN processes the data. The experiment results show that the output of AGLSTM outperforms with an accuracy of 99.81% and requires only a short time for training and prediction.

show abstract

“…The exchange rate is a critical factor in economic policy and financial stability (Rady et al, 2021). Additionally, the exchange rate influences the availability of foreign currency, allowing countries to utilize tourism revenue for infrastructure development and to enhance their competitiveness (Datta et al, 2021;Karakostas, 2021). Hence, the selection of an appropriate exchange rate regime is a critical aspect of fostering business expansion (Zhao, 2020;Hoang et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

The Impact of Price Fairness on the Perceived Value and Customer Satisfaction Under the Exchange Rate Change in Hotels in Egypt

Rady,

Abdelaziz,

Touni

2023

Journal of Association of Arab Universities for Tourism and Hos

View full text Add to dashboard Cite

Economic policies and exchange rate fluctuations significantly impact the hotel industry. These changes force hotels to focus on providing value based on customer purchasing power. Customers compare prices with the benefits gained from products or services provided. Therefore, price fairness is crucial to determining value and customer satisfaction. Specifically, when the value of the product or service matches the price. Based on the current change in the exchange rate and its impact on prices and customers' evaluations of products and services in hotels, and a lack of previous studies that dealt with the topic in Egypt. The research developed and examined a conceptual model grounded on three theoretical perspectives; equity theory, dual entitlement theory, and expectation-disconfirmation theory. The proposed model investigated the relationship between price fairness, perceived value, and customer satisfaction under the exchange rate change in hospitality industry in Egypt. Both paper-based questionnaires and web-based questionnaires were distributed to a stratified random sample of 384 guests in three, four, and five-star hotels in the Red Sea and Luxor governorates. The results show that the change in the Egyptian pound exchange rate increased food and beverage prices, and accommodation prices in hotels, moreover had a positive impact on the tourists' decision to purchase. Additionally, price fairness affects both the perceived value (functional, emotional, social, and value for money, and customer satisfaction. Moreover, perceived value acts as a mediator in the relationship between price fairness and customer satisfaction. This research contributes to filling a knowledge gap and offers practical implications. https://jaauth.journals.ekb.eg / customer satisfaction under the exchange rate change in hotels in Egypt, (4) investigate the impact of perceived value on customer satisfaction under the exchange rate change in hotels in Egypt, (5) explore the mediating role of perceived value in the relationship between price fairness and customer satisfaction under the exchange rate change in hotels in Egypt, (6) provide recommendations that may contribute to filling the knowledge gap and offer practical implications. Literature Review 2.1. Exchange Rate ConceptThe exchange rate, defined as the number of foreign currency units required to convert one domestic currency unit, serves as a crucial determinant of the foreign currency's value relative to the home country's currency (Katmas & Indarningsih, 2022;Soukotta et al., 2023). Moreover, the exchange rate establishes the value of foreign currency against the currency of the home country (Alstadheim et al., 2021). Furthermore, the exchange rate is described as "the connection between two connected currencies or the value of one currency for conversion to another" (Lezar, 2023, p. 89). The International Monetary Fund (IMF) prepared a rigorous methodology to calculate the weighted average exchange rate, through analyzing the proportion of transactions conducted at variou...

show abstract

Foreign Currency Exchange Rate Prediction Using Bidirectional Long Short Term Memory

Cited by 6 publications

References 11 publications

Forecasting Exchange Rate Depending On The Data Volatility: A Comparison Of Deep Learning Techniques

Forecasting Exchange Rate Depending On The Data Volatility: A Comparison Of Deep Learning Techniques

Analysis and Prediction of COVID-19 Multivariate Data Using Deep Ensemble Learning Methods

The Impact of Price Fairness on the Perceived Value and Customer Satisfaction Under the Exchange Rate Change in Hotels in Egypt

Contact Info

Product

Resources

About