TES Processes and ARIMA Models: A Comparison of Forecasting Performance

Forecasting is of prime importance for accuracy in decision-making. For data sets containing high autocorrelations, failure to account for temporal dependence will result in poor forecasting. TES (Transform-Expand-Sample) is a class of stochastic processes to model empirical autocorrelated time series and is frequently used in Monte Carlo simulation. Its merit is to capture simultaneously both the empirical distribution function and the autocorrelation function of a stochastic process. In addition, its analytical background makes it a viable tool to forecast future values of time series data. In this paper, we utilize phase-type random variables as the innovation density in the TES model fitting methodology, and we investigate the forecasting performance of TES processes