JARINGAN SARAF TIRUAN DALAM MEMPREDIKSI SUKUK NEGARA RITEL BERDASARKAN KELOMPOK PROFESI DENGAN BACKPROPOGATION DALAM MENDORONG LAJU PERTUMBUHAN EKONOMI

State Retail Sukuk is a Sharia Securities issued and its sale is regulated by the State, namely the Ministry of Finance (Depkeu). Where the government will choose the seller agent and consulting retail sukuk law. Selling agents must be obliged to have a commitment to the government in the development of the sukuk market and experience in selling Islamic financial products. The publication of this instrument is likened to a "mutualist symbiosis" between the Government and Society, both of which benefit equally. The government as the publisher benefits from the use of funds from the community, while the community benefits from investments made. This research contributes to the government and the Bank to be able to promote maximally for the next sukuk issuer. The data used is data from kemenkeu through website www.djppr.kemenkeu.go.id. The data are sukuk sales data with series 001 - 007 which are grouped into several categories namely geography, profession and age category. Algorithm used in this research is Artificial Neural Network with Backpropogation method. The input variables used are PNS (X1), Private Officer (X2), IRT (X3), Entrepreneur (X4), TNI / Polri (X5) and Others (X6) with architectural model of training and testing of 6 architectures 6-2-1, 6-5-1, 6-2-5-1 and 6-5-2-1. The output (output) generated is the best pattern of the ANN architecture. The best architectural model is 6-5-2-1 with epoch 37535, MSE 0.0009997295 and 100% accuracy rate. From this model will be conducted sensitivity analysis to see the variable that has the best performance and obtained variable Private Employees (X2) with a score of 0.3268. So obtained the results of the most investors predicted on the purchase of sukuk for the next 008 series based on the profession category is Private Employees. Keywords: Sukuk, JST, Backpropogation, Sensitivity Analysis and PredictionSukuk Ritel Negara adalah Surat berharga Syariah yang diterbitkan dan penjualannya diatur oleh Negara, yaitu Departemen Keuangan (depkeu). Dimana pemerintah akan memilih agen penjual dan konsultasi hukum sukuk ritel. Agen penjual haruslah wajib memiliki komitmen terhadap pemerintah dalam pengembangan pasar sukuk dan berpengalaman dalam menjual produk keuangan syariah. Penerbitan instrumen ini diibaratkan sebuah “simbiosis mutualis” antara Pemerintah dan Masyarakat, dimana keduanya sama-sama memperoleh keuntungan. Pemerintah selaku penerbit memperoleh keuntungan berupa penggunaan dana dari masyarakat, sedangkan masyarakat memperoleh keuntungan dari investasi yang dilakukan. Penelitian ini memberikan kontribusi bagi pemerintah dan Bank untuk dapat melakukan promosi secara maksimal untuk penerbitat sukuk berikutnya. Data yang digunakan adalah data dari kemenkeu melalui website www.djppr.kemenkeu.go.id. Data tersebut adalah data penjualan sukuk dengan seri 001 – 007 yang dikelompokkan dalam beberapa kategori yakni geografis, profesi dan kategori umur. Algoritma yang digunakan pada penelitian ini adalah Jaringan Saraf Tiruan dengan metode Backpropogation. Variabel masukan (input) yang digunakan adalah PNS (X1), Pegawai Swasta (X2), IRT (X3), Wiraswasta (X4), TNI/Polri (X5) dan Lainnya (X6) dengan model arsitektur pelatihan dan pengujian sebanyak 6 arsitektur yakni 6-2-1, 6-5-1, 6-2-5-1 dan 6-5-2-1. Keluaran (output) yang dihasilkan adalah pola terbaik dari arsitektur JST. Model arsitektur terbaik adalah 6-5-2-1 dengan epoch 37535, MSE 0,0009997295 dan tingkat akurasi 100%. Dari model ini akan dilakukan analisis sensivitas untuk melihat variabel yang memiliki performa terbaik dan diperoleh variabel Pegawai Swasta (X2) dengan skor 0,3268. Sehingga didapat hasil prediksi investor terbanyak pada pembelian sukuk untuk seri 008 berikutnya berdasarkan kategori profesi adalah Pegawai Swasta.Kata Kunci: Sukuk, JST, Backpropogation, Analisis Sensivitas dan Prediksi

Download Full-text

Artificial Neural Network with Backpropogation Method in Predicting Sukuk Retail State Based on Age Categories in Promoting Economic Growth

10.31227/osf.io/rjse5 ◽

2018 ◽

Author(s):

dedisuhendro

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Data Series ◽

Accuracy Rate ◽

Public Funds ◽

The Public ◽

Artificial Neural ◽

Input Variables ◽

The Government ◽

Age Category

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 <25 (X1), agecategory 25 - 40 (X2), age category 41 - 55 (X3), and 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.

Download Full-text

ANALISIS JARINGAN SYARAF TIRUAN METODE BACKPROPOGATION DALAM MEMPREDIKSI KETERSEDIAAN KOMODITAS BERAS BERDASARKAN PROVINSI DI INDONESIA

Jurnal RESISTOR (Rekayasa Sistem Komputer) ◽

10.31598/jurnalresistor.v2i2.358 ◽

2019 ◽

Vol 2 (2) ◽

pp. 105-118

Author(s):

Abdullah Ahmad ◽

Pipit Mutiara Putri ◽

Winanda Alifah ◽

Solikhun Solikhun

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Food Security ◽

Accuracy Rate ◽

National Statistics ◽

Architectural Model ◽

Human Need ◽

Backpropagation Method ◽

Input Variables ◽

The Government

Food is a major human need that must be completed at any time. This right is one of human rights, stated in article 27 of the 1945 Constitution and in the Rome Declaration (1996). These considerations underlie the issuance of Law No. 7/1996 concerning Food. With these considerations, the Government always considers increasing food security related to increasing domestic production. This research is expected to contribute to the government in order to predict the contribution of rice by province in Indonesia. The data used is data from the National Statistics Agency through the website www.bps.go.id. The data is data on rice / rice production based on provinces in Indonesia in the period of 2010 to 2015. The algorithm used in this study is Artificial Neural Networks with the Backpropagation method. The input (input) variables used are data for 2010 (X1), data for 2011 (X2), data for 2012 (X3), data for 2013 (X4), data for 2014 (X5) and data for 2015 as targets with models training and testing architecture of 4 architectures namely 4-4-1, 4-8-1, 4-16-1, 4-32-1. The resulting output is the best pattern of ANN architecture. The best architectural model is 4-4-1 with 218 days, MSE 0.012728078 and an accuracy rate of 97%. From this model obtained from estimates obtained from provinces in Indonesia.

Download Full-text

JARINGAN SYARAF TIRUAN DALAM MEMPREDIKSI JUMLAH PRODUKSI DAGING SAPI BERDASARKAN PROVINSI

KOMIK (Konferensi Nasional Teknologi Informasi dan Komputer) ◽

10.30865/komik.v2i1.941 ◽

2018 ◽

Vol 2 (1) ◽

Author(s):

Ahmad Revi ◽

Solikhun Solikhun ◽

M Safii

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Meat Production ◽

Beef Production ◽

Architectural Model ◽

Architectural Models ◽

Artificial Neural ◽

Input Variables ◽

The Government ◽

Target Data

Prediction is a process for estimating how many needs will be in the future. This study aims to predict the amount of beef production by province. Beef is one source of protein which is also a high value comodities. Meat production in Indonesia in general tends to increase by around 2.76% per year. But along with the increase in beef production in Indonesia, the level of meat consumption in Indonesia tends to fluctuate in recent years. Imports are the most common step taken by the government to meet domestic beef needs. By using the Artificial Neural Network and backpropagation algorithm, it will be predicted the amount of beef production based on the province in order to determine the steps to meet domestic beef demand based on the amount of beef consumption in the community. This study uses 11 input variables, namely data from 2005 to 2016 with 1 target, data of 2017. Using 5 architectural models to test the data to be used for prediction, the 11-4-1 model, 11-8-1 , 11-18-1, 11-20-1 and 11-28-1. Obtained the results of the best architectural model is the 11-28-1 architectural model with truth accuracy of 100%, the number of epochs 15 and MSE is 0.008623197. This model will be used in predicting the amount of beef production by province.Keywords : Beef production, prediction, backpropagatin, Artificial Neural Network

Download Full-text

ANALISIS JARINGAN SYARAF TIRUAN METODE BACKPROPOGATION DALAM MEMPREDIKSI KETERSEDIAAN KOMODITAS BERAS BERDASARKAN PROVINSI DI INDONESIA

Jurnal RESISTOR (Rekayasa Sistem Komputer) ◽

10.31598/jurnalresistor.v2i1.348 ◽

2019 ◽

Vol 2 (1) ◽

pp. 48-60

Author(s):

Abdullah Ahmad ◽

Pipit Mutiara Putri ◽

Winanda Alifah ◽

Indra Gunawan ◽

Solikhun .

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Food Security ◽

Accuracy Rate ◽

National Statistics ◽

Architectural Model ◽

Human Need ◽

Backpropagation Method ◽

Input Variables ◽

The Government

Download Full-text

Prediction Model of Iron Ore Pellet Ambient Strength and Sensitivity Analysis on the Influence Factors

Metals ◽

10.3390/met8080593 ◽

2018 ◽

Vol 8 (8) ◽

pp. 593 ◽

Cited By ~ 1

Author(s):

Qiangjian Gao ◽

Yingyi Zhang ◽

Xin Jiang ◽

Haiyan Zheng ◽

Fengman Shen

Keyword(s):

Neural Network ◽

Sensitivity Analysis ◽

Prediction Model ◽

Bp Neural Network ◽

Back Propagation ◽

Influence Factors ◽

Principal Component ◽

Bp Network ◽

Input Variables ◽

Artificial Neural Network Ann

The Ambient Compressive Strength (CS) of pellets, influenced by several factors, is regarded as a criterion to assess pellets during metallurgical processes. A prediction model based on Artificial Neural Network (ANN) was proposed in order to provide a reliable and economic control strategy for CS in pellet production and to forecast and control pellet CS. The dimensionality of 19 influence factors of CS was considered and reduced by Principal Component Analysis (PCA). The PCA variables were then used as the input variables for the Back Propagation (BP) neural network, which was upgraded by Genetic Algorithm (GA), with CS as the output variable. After training and testing with production data, the PCA-GA-BP neural network was established. Additionally, the sensitivity analysis of input variables was calculated to obtain a detailed influence on pellet CS. It has been found that prediction accuracy of the PCA-GA-BP network mentioned here is 96.4%, indicating that the ANN network is effective to predict CS in the pelletizing process.

Download Full-text

Bayesian and Sensitivity Analysis Approaches to Modelling the Direct Solar Irradiance

Solar Energy ◽

10.1115/isec2005-76224 ◽

2005 ◽

Author(s):

Philippe Lauret ◽

Mathieu David ◽

Eric Fock ◽

Laetitia Adelard

Keyword(s):

Neural Network ◽

Sensitivity Analysis ◽

Solar Irradiance ◽

Second Step ◽

Practical Implementation ◽

Bayesian Techniques ◽

Systematic Methodology ◽

Important Input ◽

Input Variables ◽

Selection Of

In this paper, emphasis is put on the design of a neural network to model the direct solar irradiance. Since unfortunately a neural network (NN) is not a statistician in-a-box, building a NN for a particular problem is a non trivial task. As a consequence, we argue that in order to properly model the direct solar irradiance, a systematic methodology must be employed. For this purpose, we propose a two-step approach to building the NN model. The first step deals with a probabilistic interpretation of the NN learning by using Bayesian techniques. The Bayesian approach to modelling offers significant advantages over the classical NN learning process. Among others, one can cite a) automatic complexity control of the NN using all the available data b) selection of the most important input variables. The second step consists in using a new sensitivity analysis-based pruning method in order to infer the optimal NN structure. We show that the combination of the two approaches makes the practical implementation of the Bayesian techniques more reliable.

Download Full-text

Penerapan Algoritma Backpropagation dalam Memprediksi Hasil Panen Tanaman Sayuran

BIOS : Jurnal Teknologi Informasi dan Rekayasa Komputer ◽

10.37148/bios.v2i1.18 ◽

2021 ◽

Vol 2 (1) ◽

pp. 21-29

Author(s):

Dio Hutabarat ◽

Solikhun ◽

M. Fauzan ◽

Agus Perdana Windarto ◽

Fitri Rizki

Keyword(s):

Evaluation System ◽

Crop Yields ◽

Vegetable Crop ◽

Accuracy Rate ◽

Backpropagation Algorithm ◽

The People ◽

Architectural Model ◽

Data Source ◽

The Government ◽

Food Needs

This study aims to see the development of the number of vegetable crop yields in the following year. With this prediction, it is hoped that it can help the government and the community to be more careful in increasing the supply of crop stocks in order to meet the food needs of the people of Simalungun Regency. The data source is obtained from the Central Bureau of Statistics. In this study, researchers used the Backpropagation Algorithm. The Backpropagation Algorithm is an algorithm that functions to reduce the error rate by adjusting the weight based on the desired output and target. The results of this study show that the best architectural model is the 2-1-1 model with an accuracy rate of 75.0% and an epoch of 1392 iterations in 00:07 seconds. This research is expected to be a reference material in other studies that have the same research object and as a consideration for the government in making an even more accurate evaluation system

Download Full-text

Two-way interaction of input variables in the sensitivity analysis of neural network models

Ecological Modelling ◽

10.1016/j.ecolmodel.2005.11.008 ◽

2006 ◽

Vol 195 (1-2) ◽

pp. 43-50 ◽

Cited By ~ 55

Author(s):

Muriel Gevrey ◽

Ioannis Dimopoulos ◽

Sovan Lek

Keyword(s):

Neural Network ◽

Sensitivity Analysis ◽

Network Models ◽

Neural Network Models ◽

Input Variables

Download Full-text

Driving Risk Detection Model of Deceleration Zone in Expressway Based on Generalized Regression Neural Network

Journal of Advanced Transportation ◽

10.1155/2018/8014385 ◽

2018 ◽

Vol 2018 ◽

pp. 1-8 ◽

Cited By ~ 3

Author(s):

Weiwei Qi ◽

Zhexuan Wang ◽

Ruru Tang ◽

Linhong Wang

Keyword(s):

Neural Network ◽

Prediction Accuracy ◽

Drunk Driving ◽

Mobile Internet ◽

Generalized Regression Neural Network ◽

Accuracy Rate ◽

Velocity Difference ◽

Detection Model ◽

Driving Risk ◽

Input Variables

Drivers’ mistakes may cause some traffic accidents, and such accidents can be avoided if prompt advice could be given to drivers. So, how to detect driving risk is the key factor. Firstly, the selected parameters of vehicle movement are reaction time, acceleration, initial speed, final speed, and velocity difference. The ANOVA results show that the velocity difference is not significant in different driving states, and the other four parameters can be used as input variables of neural network models in deceleration zone of expressway, which have fifteen different combinations. Then, the detection model results indicate that the prediction accuracy rate of testing set is up to 86.4%. An interesting finding is that the number of input variables is positively correlated with the prediction accuracy rate. By applying the method, the dangerous state of vehicles could be released through mobile internet as well as drivers' start of risky behaviors, such as fatigue driving, drunk driving, speeding driving, and distracted driving. Numerical analyses have been conducted to determine the conditions required for implementing this detection method. Furthermore, the empirical results of the present study have important implications for the reduction of crashes.

Download Full-text

Elman's Recurrent Neural Network Applied to Forecasting Algal Dynamic Variation in Gonghu Bay

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.779-780.1352 ◽

2013 ◽

Vol 779-780 ◽

pp. 1352-1358

Author(s):

He Yi Wang ◽

Xu Chang Yang

Keyword(s):

Neural Network ◽

Sensitivity Analysis ◽

Environmental Factors ◽

Recurrent Neural Network ◽

Conceptual Models ◽

Lake Taihu ◽

Data Set ◽

Dynamic Variation ◽

Daily Data ◽

Input Variables

This paper describes the training, validation and application of recurrent neural network (RNN) models to computing the algal dynamic variation at three sites in Gonghu Bay of Lake Taihu in summer. The input variables of Elmans RNN were selected by means of the canonical correspondence analysis (CCA) and Chl_a concentration as output variable. Sequentially, the conceptual models for Elmans RNN were established and the Elman models were trained and validated on daily data set. The values of Chl_a concentration computed by the models were closely related to their respective values measured at the three sites. The correlation coefficient (R2) between the predicted Chl_a concentration by the model and the observed value were 0.86-0.92. And sensitivity analysis was performed to clarify the algal dynamic variation to the change of environmental factors. The results show that the CCA can efficiently ascertain appropriate input variables for Elmans RNN, the Elmans RNN can precisely forecast the Chl_a concentration at three different sites in Gonghu Bay of Lake Taihu in summer and sensitivity analysis validated the algal dynamic variation to the change of environmental factors which were selected by CCA.

Download Full-text