Year: 2024
Type: article
Abstract: Currency risk is one of the dominant risk factors that financial institutions constantly face, especially in the context of globalisation and integration of financial markets. Its relevance is significantly increased by the high volatility of exchange rates, political instability and other macroeconomic turbulences that characterise the modern economic environment. Inadequate assessment and management of foreign exchange risk can lead to significant financial losses for a banking institution and, in some cases, to its failure.Modern trends in the development of financial markets, such as the growing role of unstructured data and new technologies, require the development of new methodological approaches to currency risk assessment. At the same time, the existing arsenal of tools needs to be further developed. The use of more complex and accurate models will enable banks to manage their currency risks more effectively and increase their resilience to external shocks.The objective of the study is to develop a comprehensive approach to currency risk assessment based on modern instrumental forecasting methods, in particular time series analysis methods, factor analysis, regression analysis and neural networks in the bank's risk management system in the context of digitalisation.The results of the study demonstrate the effectiveness of the proposed approach. Factor analysis and regression analysis were used to identify the key factors influencing the dynamics of the main currencies, namely the euro, US dollar and pound sterling exchange rates. The constructed neural networks allowed the generation of reliable forecasts of exchange rates, which is a necessary condition for effective currency risk management in the risk management system. The results obtained can be used by banks to develop effective modelling of behavioural scenarios under risk and to develop successful hedging strategies.
Author: Yuliya Kolomiiets
Institution: V. N. Karazin Kharkiv National University
Language: English
Subfield: Accounting
Domain: Social Sciences
Open Access status: diamond
OpenAlex ID: W4411307693