Banks in India need to figure out how much money they should keep aside to cover risks in their investments. The Reserve Bank of India wants them to use a method called Value-at-Risk (VaR) to do this. The study looked at different ways to estimate VaR for foreign exchange rate risks in banks. They found that when returns are not normal, using a normal distribution to estimate VaR can lead to underestimating the risk. The most accurate VaR estimates came from using a model based on Student’s t-distribution.