Machine Learning Algorithm for Determining the Best Performance in Predicting Turmeric Production in Indonesia

Abstract

The herb that has many uses in everyday life is turmeric. Not only in Indonesia but in other countries also use turmeric for consumption. Therefore, by making predictions on the level of turmeric production in the country, so that the government or other parties can use this as a reference and reference to solve problems. The method we use is Resilient Backpropagation where this method is one of the methods that is often used to forecast data. By using turmeric plant production data in Indonesia from 2016-2021 taken on the website of the Indonesian Central Statistics Agency. According to the data to be tested a network architecture model is formed, namely 2-15-1, 2-20-1, 2-25- 1 and 2-30-1. From this model, the Fletcher-Reeves method is used. From the 4 models that have been trained and tested, a 2-15-1 model is obtained to be the best architectural model for each method. The accuracy level of the Fletcher-Reeves method with the 2-15-1 model has an MSE value of 0.002481597.