WEIGHT OPTIMIZATION WEIGHTED MOVING AVERAGE WITH PARTICLE SWARM OPTIMIZATION IN PREDICTION OF RUBBER PRODUCTION LEVELS

Abstract

Rubber is a mainstay commodity in the country, in 2014 Indonesia ranked second as the largest natural rubber producing country in the world. However, rubber production in Indonesia experiences uncertain ups and downs so it is necessary to predict it in order to benefit small farmers and the state. Weighted Moving Average ( WMA) is a method for predicting time series data. However, the parameters on the WMA need to be optimized in order to get optimal weight results on the WMA and get accurate results. Algorithm Particle Swarm Optimization implemented to determine the weight value of the method Weighted Moving Average more optimal. PSO-WMA and WMA were carried out on three weights, namely from weighting 3 4 and 5 on rubber production data. So that the results of this study are WMA with 3 weights get 81% accuracy, 4 weight 80.5% and 5 weight 80.3%. And for PSO-WMA,  the   accuracy at weighting 3 is 81.4%, weighting 4 is 80.9% and for weighting 5 it is 81.6%. The test results     of this study have the effect of the weight value on WMA in increasing the accuracy results.