Resumen
This study investigates whether different specifications of univariate GARCH models can usefully forecast volatility on the foreign exchange market. The study uses only forecasts from an asymmetric GARCH model, namely Exponential GARCH (EGARCH) for CHF/RON exchange-rate pair for the period January 2010 to February 2020. The dataset is obtained from ?Investing.com? and covers the daily closing prices for the CHF/RON across the mentioned period. The data encompasses the period when hundreds of thousands of holders of Swiss franc mortgages across Romania suddenly found themselves facing higher loan repayments of up to 20 per cent when the Swiss National Bank (SNB) scrapped its policy of the minimum exchange-rate of 1.2 Swiss francs against the Euro on January 15, 2015. To reduce the burden of more currency fluctuations, Romania looked at the Hungarian experience of converting Swiss franc mortgage loans to domestic or euro denominated loans. This process will be known as loan conversion program. In this program, households had the option to choose whether they will be willing to convert their Swiss franc denominated mortgage loans to domestic currency loans or to maintain their mortgage loans in Swiss francs. Undoing CHF-denominated mortgage loans has several consequences for macroprudential and macroeconomic policy. However, a significant benefit of loan conversion for the financial system is the diminution of the exposure of the banks across Romania to systemic exchange-rate risks to their balance sheet through domestic currency depreciation. The European Central Bank (ECB) warned on several occasions that foreign currency loans represent a major risk to financial stability. This paper reaches the conclusion that the EGARCH model could be used to predict volatility of the currencies in the future.