Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Wildansyah Maulana Rahmat
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Prediksi Penjualan Ponsel Pintar menggunakan Metode Jaringan Syaraf Tiruan Backpropagation Kombinasi Particle Swarm Optimization Wildansyah Maulana Rahmat; Nurul Hidayat; Arief Andy Soebroto
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 7 No 1 (2023): Januari 2023
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The use of smartphones in Indonesia tends to increase. Smartphone users alone have reached 28% of the total Indonesian population in 2019 and experienced an increase of 2% from the previous year. In certain months mobile phone sales can increase rapidly and may also decline. But often some phones go unsold for months and find that the selling price is decreasing. Therefore, an effort is needed to reduce the losses from this and increase profits. Taking into account the number of phones to be restocked one way to reduce losses on phones that have not been sold for a long time. Manfaat Cell is a mobile phone sales store domiciled in Karangploso, East Java. Over time some phones were not sold according to the target in the month due to the large number of goods but the interest of buyers was small, it took a plan for the number of products to be restocked, one of which was to implement a method to predict the number of goods to be restocked. The prediction system uses the backpropagation method and is optimized using particle swarm optimization. The data used is monthly Cell Benefit sales data from 2018 to 2021, with a 70% share for training data and 30% for testing data. The result of the backpropagation performance of the particle swarm optimization combination is a MAPE value of 3.453%, which is obtained from the combination of optimal parameters, namely input as many as 3, hidden as many as 3, output as many as 1, number of iterations as many as 200, inertia weight value of 0.9, and the number of pop sizes as many as 40.
Co-Authors Arief Andy Soebroto Nurul Hidayat