An ARIMA model is a statistical technique to predict time series (Box et al., 2008). SARIMA takes into account the seasonal elements in the data with ARIMA modeling. The ARIMA model can be converted to SARIMA model by including seasonal autoregressive, seasonal moving average and seasonal differencing operators. If the time series Xt is modeled as SARIMA ðp; d; qÞ x ðP; D; QÞS process, it can be stated as (Cools et al., 2009; Aburto and Weber, 2007):