Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Simtek : Jurnal Sistem Informasi dan Teknik Komputer
Jumadil Nangi
Jurusan Informatika, Fakultas Teknik, Universitas Halu Oleo, Kendari, Indonesia
Computer Science & IT Electrical & Electronics Engineering Engineering

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

Found 2 Documents
Search

 1 
SISTEM REKOMENDASI PRODUK UMKM KOTA KENDARI BERBASIS WEBSITE DENGAN PENERAPAN ALGORITMA NEURAL COLLABORATIVE FILTERING DAN K-NEAREST NEIGHBOR Muhammad Saharullah Raiya; Jumadil Nangi; La Ode Muhammad Bahtiar Aksara; Bambang Pramono; Isnawaty; Kobajashi Togo Isamu
Simtek : jurnal sistem informasi dan teknik komputer Vol. 11 No. 1 (2026): April 2026
Publisher : STMIK Catur Sakti Kendari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51876/simtek.v11i1.1769

Abstract

The rapid growth of e-commerce has created significant opportunities for MSMEs in Kendari City to expand their market reach digitally; however, product visibility and service personalization remain suboptimal. This study aims to design and develop a web-based product recommendation system for MSMEs by implementing Neural Collaborative Filtering (NCF) and K-Nearest Neighbor (KNN) algorithms through a switching mechanism. KNN is used in cold-start conditions for new users based on product similarity, while NCF is applied when interaction data are available to model the non-linear relationships between users and products. The system was developed using the Rational Unified Process (RUP) method with Python and Flask technologies. Evaluation was conducted through algorithm performance testing using Top-N metrics, User Acceptance Testing (UAT), and white-box testing. The results show that NCF achieved an HR@10 of 0.7692 and an NDCG@10 of 0.4691, while KNN obtained a Precision@10 of 0.9500. UAT produced a score of 82.67%, categorized as very good, and white-box testing indicated that the logical flow of KNN and NCF operated as designed.
APLIKASI KASIR BERBASIS WEB TERINTEGRASI DENGAN LAPORAN PENJUALAN MENGGUNAKAN ALGORITMA FLUXSORT (STUDI KASUS: TOKO JOEL, KELURAHAN PUNGGOLAKA, KOTA KENDARI) Laode Ikhwanul Uzlah; Statiswaty Statiswaty; Jumadil Nangi
Simtek : jurnal sistem informasi dan teknik komputer Vol. 11 No. 1 (2026): April 2026
Publisher : STMIK Catur Sakti Kendari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51876/simtek.v11i1.1772

Abstract

Manual transaction recording in a business triggers calculation errors, difficulties in data retrieval, and delays in reporting. This study aims to develop a web-based cashier application by implementing the Fluxsort algorithm as a data sorting method at the application layer. The system is built using Python/Flask and an SQLite database, and operates offline on a local network. The Fluxsort algorithm is integrated to sort the product list in the Cashier module and sales aggregation reports in the Admin module. This approach effectively avoids repeated query latency on the database server and handles multi-table aggregation values. Functional testing results achieved a 100% success rate across 11 test scenarios. Performance testing proved that the Fluxsort algorithm is capable of completing the sorting of 1,000 random data entries in 16.508 milliseconds. Black Box Testing validated 20 interface scenarios with 100% valid results. User Acceptance Testing (UAT) involving 5 respondents yielded a feasibility index of 91% (Very Good). Therefore, this system is rated Very Feasible and reliable as a digitalization solution for MSME operational needs.
Co-Authors Bambang Pramono Isnawaty Kobajashi Togo Isamu La Ode Muhammad Bahtiar Aksara Laode Ikhwanul Uzlah Muhammad Saharullah Raiya Statiswaty Statiswaty