Implementasi Metode Double Exponential Smoothing Untuk Prediksi Hasil Panen Sayuran Kentang

Abstract

   Potato plants have great potential as a source of carbohydrates for human needs. Potato yields are very influential in meeting food needs, so a system that is able to predict the amount of potato production is needed in order to be able to meet the production of potato harvests every year as a material for consideration and recommendations for the amount of potato production each year so that the need for the next market demand can be met. In addition, farmers can determine the amount of land area for planting potato vegetables. This study aims to implement the double exponential smoothing method in a decision support system for predicting potato crop yields, using this technique to help potato farmers/managers in recording crop yields per month and every year. Harvest data from the previous 6 years is used as training data, to find predictive data for the following year's harvest. From the results of the study, the best alpha value used to predict was 0.5 with an accuracy of 82.9%.