Article Per Year (5 Year)
p-Index From 2019 - 2024
0.408
P-Index
This Author published in this journals
All Journal Jurnal Indonesia : Manajemen Informatika dan Komunikasi Jurnal Indonesia : Manajemen Informatika dan Komunikasi
Sahroni
Sekolah Tinggi Ilmu Komputer Cipta Karya Informatika
Computer Science & IT Languange, Linguistic, Communication & Media Library & Information Science

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
PENERAPAN METODE NEURAL NETWORK DENGAN STRUKTUR BACKPROPAGATION UNTUK MEMPREDIKSI KEBUTUHAN STOK PADA TOKO UMKM PERLENGKAPAN BAYI BABYQU Dadang Iskandar Mulyana; YkhSanur; FikriYadi; Sahroni; Agus Sigit Sumarsono
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 4 No. 1 (2023): Jurnal Indonesia : Manajemen Informatika dan Komunikasi (JIMIK)
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) AMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jimik.v4i1.131

Abstract

At this time Machine Learning especially Deep Learning is developing very quickly in any field, especially in the fields of business, transactions, stock predictions, sales, and stocks and the like. Machine Learning has become a mainstay for facilitating and helping work. At the BabyQu store, the decisions used to carry out stock inventory still use the manual method, and there are several problems that arise including the occurrence of excess stock which makes other storage areas used for excess stock, especially if there are products that have an expiration date, and if there is a shortage of stock, problems will occur that will make consumers who need products or goods go to other places and several other problems that will arise which will cause losses to BabyQu stores, it is necessary to create a system or software that aims to assist BabyQu stores in forecasting stock availability product to overcomesome of these problems. This research was made using the Artificial Neural Network (ANN) model design and method using Backpropagation as the algorithm because this algorithm can reduce the percentage of errors. The results we got in this study using the 3-3-1 model obtained an accuracy rate of 85.72%, using 550 iterations of epochs, and taking approximately 11.1 seconds.
PENERAPAN METODE NEURAL NETWORK DENGAN STRUKTUR BACKPROPAGATION UNTUK MEMPREDIKSI KEBUTUHAN STOK PADA TOKO UMKM PERLENGKAPAN BAYI BABYQU Dadang Iskandar Mulyana; YkhSanur; FikriYadi; Sahroni; Agus Sigit Sumarsono
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 4 No. 1 (2023): Jurnal Indonesia : Manajemen Informatika dan Komunikasi (JIMIK)
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jimik.v4i1.131

Abstract

At this time Machine Learning especially Deep Learning is developing very quickly in any field, especially in the fields of business, transactions, stock predictions, sales, and stocks and the like. Machine Learning has become a mainstay for facilitating and helping work. At the BabyQu store, the decisions used to carry out stock inventory still use the manual method, and there are several problems that arise including the occurrence of excess stock which makes other storage areas used for excess stock, especially if there are products that have an expiration date, and if there is a shortage of stock, problems will occur that will make consumers who need products or goods go to other places and several other problems that will arise which will cause losses to BabyQu stores, it is necessary to create a system or software that aims to assist BabyQu stores in forecasting stock availability product to overcomesome of these problems. This research was made using the Artificial Neural Network (ANN) model design and method using Backpropagation as the algorithm because this algorithm can reduce the percentage of errors. The results we got in this study using the 3-3-1 model obtained an accuracy rate of 85.72%, using 550 iterations of epochs, and taking approximately 11.1 seconds.
Co-Authors Agus Sigit Sumarsono Dadang Iskandar Mulyana` FikriYadi YkhSanur