Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal JIKSI (Jurnal Ilmu Komputer dan Sistem Informasi) Jurnal Esensi Infokom : Jurnal Esensi Sistem Komputer dan Informasi
Matthew Oni
Unknown Affiliation
Computer Science & IT Mathematics Other

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

Found 2 Documents
Search

 1 
PREDIKSI HARGA PANGAN KOTA BANDUNG MENGGUNAKAN METODE GATED RECURRENT UNIT Matthew Oni; Manatap Dolok Lauro; Teny Handhayani
Jurnal Ilmu Komputer dan Sistem Informasi Vol. 11 No. 2 (2023): JURNAL ILMU KOMPUTER DAN SISTEM INFORMASI
Publisher : Fakultas Teknologi Informasi Universitas Tarumanagara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24912/jiksi.v11i2.26014

Abstract

Food problems often occur among the community, this occurs due to a lack of predictions made to determine future food prices. Food prices can be achieved if the government can provide sufficient food supplies both in terms of quality and quantity. The availability of sufficient food is an important factor in maintaining the health and welfare of the community. However, the high price fluctuations of staple foods in traditional markets have a negative impact on the availability and quality of food for the community, especially those with low incomes. This was caused by various factors such as rising raw material prices, the influence of weather factors, and changes in people's consumption patterns. In addition, the process of distribution and marketing of staple foods in traditional markets in Bandung City, which still relies on manual processes and is less structured, can also cause high price fluctuations. Therefore we need an application to predict staple food needs for the future accurately and effectively. This study uses the Gated Recurrent Unit method. This method is used because the Gated Recurrent Unit method has good performance in making predictions and fits the data used for this study. In this study, there were 5 types of commodities used, namely rice, chicken meat, chicken eggs, shallots, and garlic. All datasets used were taken from the website of the National Strategic Food Price Information (PIHPSNasional, https://www.bi.go.id/hargapangan). Predictive results by evaluating MAE and MAPE for rice 12.8, and 0.10, for chicken meat 12.8 , and 0.10, for chicken egg 244.5, and 0.64, for onion 296.9, and 1.05, for garlic 602.8, and 1.32.
Analysis And Forecasting of Foodstuffs Prices In Bandung Using Gated Recurrent Unit Matthew Oni; Manatap Dolok Lauro; Andry Winata; Teny Handhayani@
Jurnal Esensi Infokom : Jurnal Esensi Sistem Informasi dan Sistem Komputer Vol 7 No 2 (2023)
Publisher : Institut Bisnis Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55886/infokom.v7i2.651

Abstract

Bandung adalah sebuah kota di provinsi Jawa Barat dan salah satu kota padat penduduk di Indonesia. Oleh karena itu, memprediksi dan menganalisis harga bahan pangan berdasarkan data historis bermanfaat untuk menemukan trend dan informasi yang berguna bagi pemerintah dan masyarakat. Penelitian ini mengembangkan model menggunakan gated recurrent unit or GRU yang merupakan versi spesifik dari recurrent neural network (RNN) untuk memprediksi harga daging ayam, beras, bawang merah, telur ayam, dan bawang putih di pasar tradisional Bandung. Model GRU dilatih menggunakan dataset dari Pusat Informasi Harga Pangan Strategis Nasional. Dataset dikumpulkan dari bulan Januari 2018-Februari 2023. Hasil percobaan menunjukkan bahwa GRU berhasil diimplementasikan untuk peramalan harga telur ayam, beras, bawang merah, daging ayam, dan bawang putih. Model terbaik menghasilkan Mean Absolute Error (MAE) masing-masing sebesar 338.1, 341.8, 118.3, 133.1, dan 4.3 untuk harga bawang putih, bawang merah, telur ayam, daging ayam, dan beras.
Co-Authors Andry Winata Laksono Trisnantoro Manatap Dolok Lauro, Manatap Dolok Teny Handhayani Teny Handhayani@