Comparison of Single Exponential Smoothing, Naive Model, and SARIMA Methods for Forecasting Rainfall in Medan

Abstract

This study aims to compare the best method on the forecasting system of rainfall in Medan using Single Exponential Smoothing (SES), Naive Model, and Seasonal Autoregressive Integrated Moving Average (SARIMA) . The data used in this study is rainfall data for 10 years (2009 – 2019). From the simulation by comparing existing method, the best model is SES with and value of MAPE (Mean Absolut Percentage Error) sebesar 2,47%. And then SARIMA (1,01,1)(4,0,3)12 whit value of MAPE is2,93%. Both of this model is high accurate model because value of MAPE resulted < 10%.