The article explores how different models can predict the risk of investing in Latin American stock markets. By combining GARCH models and extreme value theory, researchers found that some models are better at estimating Value at Risk (VaR) for long and short positions in Argentina and Mexico. However, these models struggle to accurately estimate Expected Shortfall (ES). Understanding fat tails, asymmetry, and long memory in stock market data is crucial for effective risk management and hedging strategies.