PENERAPAN METODE DOUBLE EXPONENTIAL SMOOTHING UNTUK PERAMALAN HARGA BERAS

St Rimayatun Naja. 2023. Implementation of the Double Exponential Smoothing Method for Price Forecasting of Rice Staples. Thesis, Department of Informatics Engineering, Faculty of Science and Technology, Nahdlatul Ulama Sunan Giri University. Main Advisor Hatie Audytra S.Kom, M.T and Co-Supervisor Auliyaur Rakhim, S.Hum, MM. Indonesia is an agrarian country with very broad food support, including producing large amounts of rice. Rice is a staple for the majority of Indonesia's population with this type of rice plant made from grains, therefore the demand for rice in Indonesia is very high. The price of rice in Indonesia follows a seasonal harvest pattern. During the harvest season, the price of rice is low, while during the non-harvest season, the price is high. Instability can also be caused by decreased production due to weather, supply sources and also transportation facilities can also affect rising prices. Based on the background of the existing problems, it is necessary to have a rice price forecasting system that has the ability to predict rice prices in the next few months. In this study using the Double Exponential Smoothing method in this method the smoothing process is carried out twice. The Double Exponential Smoothing method is used to forecast data that has an upward trend. The data used for the period 2016 to 2023, forecasting accuracy uses MSE (Mean Absolute Error) and MAPE (Mean Absolute Percentage Error). Based on the test results using the Double Exponential Smoothing method using the forecasting accuracy of MSE and MAPE, the results obtained were 13250 with an MSE value of 265625 and a MAPE value of 2,4038% with a parameter of 0.5. With the criterion of a MAPE value of <10%, this shows that the accuracy of MAPE is in the very good category.