Implementation of Bayesian Regulation Algorithm for Estimation of Production Index Level Micro and Small Industry. (August 2019)

• Record Type: Journal Article
• Authors: Afriliansyah, Teuku; Parulian, Parulian; Ulva, Ananda Faridhatul; Simanjuntak, Marthin Yohannes; Wanto, Anjar; Sihombing, Danny; Sutanto, Agus; Ginantra, NLWSR
• Is Part Of: Journal of physics. Volume 1255(2019)
• Publication Date: 2019-08
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1255/1/012027
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: Small Industry is an industrial company whose workforce consists of 5-19 people. While the Micro Industry is an industrial company whose workforce consists of 1-4 people. The purpose of this study is to estimate the Production Index of Micro and Small Industries according to KBLI for years to come. KBLI is a reference classification used to classify Indonesian economic activities/activities into several business fields/business fields that are distinguished based on the type of economic activity that produces products/outputs in the form of goods and services. In this study, the estimation method used is the Bayesian Regulation Algorithm. This algorithm is one of the Artificial Neural Networks algorithms that can solve many estimation problems by building a trained model and showing good performance. The data to be estimated in this study are data of Micro and Small Industry Production Index according to KBLI processed from the Central Board Statistics of Indonesia. This study uses 3 architectural models, namely: 5-10-20-1, 5-15-30-1 and 5-20-40-1. The best architectural model is 5-10-20-1, resulting in 83% accuracy, MSE 0.0031434897 with a minimum error of 0.001 - 0.05.