New Issue of Visnyk of the National Bank of Ukraine: Determinants of Corporate Credit Growth and Forecasting of Global Energy, Metal, and Crypto Currency Prices
The NBU has published another issue of its peer-reviewed journal Visnyk of the National Bank of Ukraine.
Topics covered in the issue:
Determinants of Corporate Credit Growth in Ukraine: The Application of Bank Lending Survey Data
In this study, Anatolii Hlazunov (NBU) investigates the determinants of corporate lending in Ukraine, with a focus on distinguishing between supply and demand factors.
The author uses a two-step procedure to build a credit standards index (CSI) based on disaggregated data from a Ukrainian bank lending survey (BLS).
First, a panel ordered logit model is used to transform categorical data into a continuous index that measures the likelihood of credit standard tightening.
Second, the research examines how this index affects new corporate lending in national and foreign currencies.
It is found that the credit standard index is influenced by:
exchange rate movements, with depreciations leading to tighter standards
bank liquidity
bank competition.
The author concludes that the CSI affects corporate loans in national currency, with a more pronounced effect on smaller banks.
Short-Term Forecasting of Global Energy and Metal Prices: VAR and VECM Approaches
In her paper for the Visnyk of the National Bank of Ukraine, Diana Balioz (NBU) explores various VAR and VECM models to forecast global prices for (crude) oil, natural gas, iron ore, and steel.
The fundamentals for metal and energy price predictions include:
stock changes
changes in commodity production volumes
export volumes by the largest players
changes in the manufacturing sector of the largest consumers
the state of global real economic activity
freight rates, recession, and more.
Kilian’s (2009) index of global real economic activity is found to be a useful proxy for global demand and a reliable input in forecasting both energy and metal prices.
The findings also suggest that models with smaller lag orders tend to outperform those with a higher number of lags.
However, individual models" performance and forecast accuracy depend on the forecast horizon.
Crypto Currency Price Forecast: Neural Network Perspectives
The study by Yuriy Kleban and Tetiana Stasiuk (National University of Ostroh Academy) examines the problem of modeling and forecasting the price dynamics of cryptocurrencies.
The authors employ the data from Binance for almost three years to model and forecast Bitcoin, Ethereum, Ripple, and Dogecoin prices.
The recurrent neural network of long-term memory showed significantly better forecasting outcomes in comparison with the Naive model, the traditional ARIMA model, and the FB Prophet based on the criteria of RMSE, MAE, and MAPE.
For Reference
Visnyk of the National Bank of Ukraine is indexed by IDEAS/RePEc, DOAJ, and others.
Visnyk of the National Bank of Ukraine has been issued to the public since September 2015.
The original language of the articles is English.
Ukrainian translations of the articles will be added later.
The judgements, conclusions, and ideas presented in the journal are those of the authors and do not necessarily reflect the views of the editorial board or the official position of the NBU.
The editorial board invites financial market experts and representatives of the banking and academic communities to contribute to the topics covered by the journal and send research materials for review and publication to: [email protected].
Paper submission is free of charge.
Translation into English and language editing are carried out by the NBU.
For more on publication requirements, please follow the link.
