Abstract: Modeling and forecasts of global oceanographic index has important implications for decision making. An effective management on climate anomalies impact depends on the performance towards better accuracy and forecasts. In this paper, an algorithm which makes use of wavelets together with a time series model, GARCH is implemented in order to improve the performance of forecasts in global climate data series. Multivariate ENSO index, MEI, for the period January, 1950 to February, 2018 is used to compare the GARCH model and a newly proposed tools with W-GARCH(1, 1) model. The goodness of performance is calculated via the Akaike information criterion, Schwarz criterion, Hannan-Quinn criterion and RMSE. The results showed that although both models fit the MEI data well, the forecast produced by the GARCH(1, 2) model underestimates the observed score while the newly proposed W-GARCH(1, 1) model generates a better accuracy of forecasts for the given data. Hence the proposed W-GARCH(1, 1) should be applied for forecasts in the fields reflected by MEI variability.