Author:
Solikhun ,Pujiastuti Lise,Wahyudi Mochamad
Abstract
Abstract
Retail Sukuk is a product of State Sharia Securities (Sukuk) issued by the Government of the Republic of Indonesia in this case the Ministry of Finance and sold to individuals or individuals of Indonesian Citizens through Selling Agents in the domestic Primary Market. This research contributes to the government and the Bank to be able to do the maximum promotion for the next sukuk issuance. The data used is data from the Ministry of Finance. These data are sukuk sales data with series 002-010 based on regional groups. The algorithm used in this study is Artificial Neural Network with Backpropogation method. Variabel masukan yang digunakan adalah kelompok wilayah bagian barat selain Jakarta (X1), kelompok Jakarta (X2), kelompok Indonesia Bagian Tengah(X3), dan kelompok Indonesia Bagian Timur (X4) dengan model arsitektur pelatihan dan pengujian sebanyak 4 arsitektur yakni 4-2-1, 4-3-1, 4-2-3-1 dan 4-3-2-1. The best architectural model is 4-3-1 with epoch 266, MSE 0.009918 and 100% accuracy rate. From this model, predictions of retail country sukuk will be made by region.
Subject
General Physics and Astronomy
Reference18 articles.
1. Analysis of Artificial Neural Network Backpropagation Using Conjugate Gradient Fletcher Reeves in the Predicting Process;Wanto;Journal of Physics: Conference Series,2017
2. Kernel functions for the support vector machine: Comparing performances on crude oil price data;Chiroma;Advances in Intelligent Systems and Computing,2014
3. Soft Solution of Soft Set Theory for Recommendation in Decision Making;Hakim;Advances in Intelligent Systems and Computing,2014
4. Comparative Performance Analysis of Negative Selection Algorithm with Immune and Classification Algorithms;Lasisi;Advances in Intelligent Systems and Computing,2014
5. Artificial Intelligence in Medicine;Hamet,2017