Artificial Neural Network with Backpropogation Method in Predicting Sukuk Retail State Based on Age Categories in Promoting Economic Growth
dedisuhendro · 2018
Sukuk Retail State has fixed remuneration that paid every month. The government gains equity from the useof public funds, while the public gets a profit from the investment. The contribution of this researchprovides benefits for promoting optimally on the next sukuk issuance. Referral data sourced from Ministryof Finance through website www.djppr.kemenkeu.go.id. The data are sukuk sales data series 003 - 009which are grouped into several categories namely geography, profession and age category. The method usedis Artificial Neural Network Backpropogation. The input variables used are age category 55 (X4) with model of trainingarchitecture and test of 4 architecture ie 4-2-1, 4-5-1, 4-2-5-1 and 4-5-2-1. The results of this study providethe best architecture 4-2-1 with epoch 1593, MSE 0.00099950214 and 71% accuracy rate. Furthermore, thesensitivity analysis was performed to determine the best performing variables, resulting in the 41-55 (X3)age category variable with a score of 0.4089. Thus obtained the prediction of most investors on the purchaseof sukuk series 010 is the age category 41 - 55.