Application of Monte Carlo simulations in banking

A vigorous advancement in the field of information technologies allows practical use of sophisticated, computing power consuming methods. One of these is the Monte Carlo simulations method, which relies on generating an immense number of stochastic scenarios and can effectively solve problems in areas such as physics or mathematics. Entities in the banking sector are constantly exposed to many kinds of risks, for instance the occurrence of negative interest rates. These risks need to be taken into account, monitored, measured and managed. Even the Monte Carlo method, usable in banking for risk measurement, has its weaknesses that need to be considered, and requires certain conditions to be met. It is crucial to correctly approximate the probability distribution and to create a sufficient number of random scenarios, to use a reliable random number generator and to bear in mind any possible sequential dependencies amongst the input data. In the practical part of this work, I analyzed the development of the London Interbank Offered Rate with a three-month maturity based on the US dollar during the years 2000 to 2016 and, using the Monte Carlo method, I tried to predict its future development as well. I came to the conclusion that the method should be used for forecasting in shorter time horizons, considering it provides significantly wider ranges of the rate's possible values at all probability levels while forecasting for longer time horizons. Via stress test, I also found that the method I applied doesn't really reflect rare short-term shocks in the resulting predictions. Neither the Monte Carlo method nor the TRADING ECONOMICS website anticipate the LIBOR USD 3M rate to fall below zero during the time horizon ending in 2020.