Abstract

AbstractThe FOREX marketplace has seen sudden boom during last couple of decades. The changes carry out a critical function in balancing the dynamics of the marketplace. As a result, the correct prediction of the change price is a critical aspect for the fulfillment of many companies and fund managers. In-spite of the reality, the marketplace is famous for its flightiness and volatility; there exists groups like agencies, banks, and pandemic for awaiting change by several techniques. The goal of this article is to locate and advocate a neural community version to forecast exchange rate to the United States dollar against Indian rupees. In this article, we have analyzed the performance of different machine learning techniques during COVID-19 pandemic situation. This is further extended to find the best model to our purpose. In this paper, we implemented three different types of techniques to predict the foreign exchange rate of US dollar against the Indian rupees with high accuracy rate, before and after the COVID-19 pandemic. The three types of neural network models implemented in this article are artificial neural network (ANN), long short-term memory network (LSTM), and gated recurring units (GRU). The results from the above three models are compared so as to find out which model performs the best as compared to other models, before and after the COVID-19 pandemic. From the empirical analysis of all the models, we concluded that GRU outperformed both ANN and LSTM. We have five sections in this article. Section 41.1 briefly describes about prediction of foreign exchange rate. In Sect. 41.2, we have discussed the methods used in this article for the prediction of foreign exchange rate. Data collection and experimental results have been discussed in Sects. 41.3 and 41.4. Finally, in Sect. 41.5, we have given the conclusion and future scope of this experimental article.KeywordsForeign exchange ratesForecastingPredictive modelNeural network (ANN)Long short-term memory (LSTM)Gated recurrent units (GRU)COVID-19

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.