MODEL PREDIKTIF UNTUK SISTEM INFORMASI LOGISTIK MENGGUNAKAN BIG DATA DAN ANALISIS SPASIAL

MARTHA PASHA ULI MANULLANG, NPM 2209400166 (2026) MODEL PREDIKTIF UNTUK SISTEM INFORMASI LOGISTIK MENGGUNAKAN BIG DATA DAN ANALISIS SPASIAL. Tugas_Akhir (Artikel) : Jurnal Sistem Informasi, Teknik Komputer Dan Teknologi Pendidikan (JUSTIKPEN) Sinta 5, 5 (2). pp. 47-50. ISSN 2828- 7921 (e-ISSN)

	Text COVER.pdf Download (4MB)
	Text ARTIKEL.pdf Restricted to Registered users only Download (387kB)

Abstract

Pengelolaan logistik yang efisien menjadi tantangan utama di tengah meningkatnya volume distribusi barang. Penelitian ini bertujuan untuk membangun model prediktif yang mengintegrasikan teknologi Big Data dan analisis spasial guna meningkatkan akurasi estimasi waktu pengiriman serta optimalisasi rute. Metode yang digunakan mencakup pemrosesan data historis pengiriman skala besar yang digabungkan dengan data spasial berbasis Geographic Information System (GIS). Temuan penting menunjukkan bahwa integrasi variabel spasial mampu meningkatkan akurasi prediksi waktu tiba menjadi 89%, atau naik sebesar 22% dibandingkan model konvensional yang hanya mencapai 73%. Kesimpulannya, model prediktif berbasis Big Data ini memberikan solusi praktis bagi pengambilan keputusan yang lebih responsif dan efisien dalam sistem informasi logistik. Kata Kunci : Big Data, Analisis Spasial, Sistem Informasi Logistik, Model Prediktif. ================================================================================================ Efficient logistics management is a major challenge amid the increasing volume of goods distribution. This study aims to build a predictive model that integrates Big Data technology and spatial analysis to improve the accuracy of estimated delivery time and route optimization. The methods used include processing historical data of large-scale shipments combined with Geographic Information System (GIS)-based spatial data. Important findings show that the integration of spatial variables is able to increase the accuracy of arrival time prediction to 89%, or an increase of 22% compared to conventional models which only reaches 73%. In conclusion, this Big Data-based predictive model provides a practical solution for more responsive and efficient decision-making in logistics information systems. Keywords : Big Data, Spatial Analysis, Logistics Information Systems, Predictive Models.

Item Type:	Article
Uncontrolled Keywords:	Big Data, Analisis Spasial, Sistem Informasi Logistik, Model Prediktif. =========================== Big Data, Spatial Analysis, Logistics Information Systems, Predictive Models.
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General)
Divisions:	Fakultas Sains Dan Teknologi > Sistem Informasi
Depositing User:	Unnamed user with email repository@ulb.ac.id
Date Deposited:	11 May 2026 09:07
Last Modified:	11 May 2026 09:07
URI:	http://repository.ulb.ac.id/id/eprint/2269

Actions (login required)

View Item