Forecasting volatility in financial time series data with GARCH
When working with financial time series data, a common task is measuring volatility, which represents uncertainty in future returns. Generally, volatility measures the spread of the probability distribution of returns over a specific period, often calculated as the variance or standard deviation (which is the square root of variance). It is used as a proxy for quantifying risk or uncertainty. In other words, it measures the dispersion of financial asset returns around an expected value. Higher volatility indicates higher risks. This helps investors understand the level of return they can expect and how often their returns will differ from the expected value.
Most of the models we discussed previously (e.g., ARIMA, SARIMA, and Prophet) focused on forecasting an observed variable based on its past values. However, these models assume a constant variance (homoskedasticity) and do not account for changes in variance over time...
