Claim Missing Document
Check
Articles

Found 7 Documents
Search

Analisis Tingkat Kepuasan Pelanggan Terhadap Pengguna Jasa Layanan Grab Menggunakan Metode C4.5 Permatasari, Veren Nita; Aula, Raisah Fajri; Akbar, Yuma; Hidayat, Aditya Zakaria
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 5 No. 3 (2024): September
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.v5i3.1002

Abstract

Technological advances have brought significant changes in various aspects of life, including transportation. Grab as one of the pioneers of online transportation services in Indonesia is the main choice for many people. However, competition among online transportation service companies forces each service provider to compete in improving the quality of their services. This study aims to analyze the level of customer satisfaction with the use of Grab services using the C4.5 method. This method was chosen because of its ability to form a decision tree model that helps identify the main factors that influence customer satisfaction. The data for this study were obtained from a survey of Grab customers who used Grab driver services within a certain period of time. The survey covered various aspects of user experience, such as Ease of Use of the Application, Service Availability, Waiting Time, Price, Security. The data was analyzed using the C4.5 algorithm to gain an in-depth understanding of the factors that influence the level of customer satisfaction. The analysis shows that the C4.5 method is effective in identifying factors that influence customer satisfaction. The results of the rapidminer test show the accuracy of the C4.5 algorithm from 100 respondent data obtained, which is 94.00%. These results are expected to provide valuable input for the Grab company and drivers in an effort to improve the quality of their services.
Classification of Customer Satisfaction with the K-Nearest Neighbor Algorithm in Relation to Employee Performance at PT. Airkon Pratama Suprianto, Ahmad; Surapati, Untung; Akbar, Yuma; Hidayat, Aditya Zakaria
International Journal Software Engineering and Computer Science (IJSECS) Vol. 4 No. 3 (2024): DECEMBER 2024
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v4i3.2948

Abstract

PT. Airkon Pratama is the technical consultancy company in the field of maintenance, repair, and operate system. Among its projects are a four-building, multi-story tax office complex. PT. Airkon Pratama experience obstacles to know how its customer satisfaction with their services that is was measured by a questionnaireobtained from work order form. The purpose of this study is to determine how well K-Nearest Neighbor data classification accurately classifies customer satisfaction based on employee performance by PT. Airkon Pratama. The data used in this study is from PT. Airkon Pratama with the data processing using RapidMiner with the K-Nearest Neighbor method which produces an accuracy of 96.53%. Among them four performance indicators were rated as "good", and two as "adequate". Of the 196 that were correctly predicted to be "good," three were "adequate." Most of the 04 respondents gave a positive response indicating their satisfaction with the management of tax office facilities provided by PT. Airkon Pratama in January 2024.
Analisis Clustering Penyakit Menular pada Manusia di Jakarta Timur Menggunakan Algoritma K-Means Ramadhan, Muhammad Arya; Poerwandono, Edhy; Akbar, Yuma; Hidayat, Aditya Zakaria
Jurnal JTIK (Jurnal Teknologi Informasi dan Komunikasi) Vol 9 No 1 (2025): JANUARI-MARET 2025
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jtik.v9i1.3007

Abstract

Humans are highly susceptible to various diseases without realizing their causes. The high incidence of infectious diseases in East Jakarta requires an analysis of distribution patterns to determine intervention priorities. This study aims to identify clusters of infectious diseases in East Jakarta, helping authorities plan effective prevention and treatment strategies. Data on infectious disease cases were obtained from the Central Statistics Agency of DKI Jakarta. The K-Means algorithm was used to cluster data based on variables such as period, region, type of disease, and number of cases. The results indicate several main clusters with distinct characteristics that can serve as a foundation for targeted strategies. From 2018 to 2021, diarrhea was predominant, making up 84.14% of cases in 2018 and 81.97% in 2019, pneumonia accounted for 32.92% in 2020, and TB Paru 33.63% in 2021. In conclusion, the K-Means algorithm effectively clusters infectious disease data and provides useful insights into disease distribution in East Jakarta, improving the impact of data-driven health programs.
Pengembangan Fitur Pencarian dan Filter Produk pada Aplikasi E-Commerce Gallery Muslim Berbasis Android Mafazi, Luthfillah; Akhsani, Ziyat; Fadillah, Fauzan; Iskandar, Dadang Mulyana; Akbar, Yuma; Hidayat, Aditya Zakaria
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 6 No. 3 (2025): September
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63447/jimik.v6i3.1587

Abstract

The primary challenge in inventory management for MSMEs like Gallery Muslim lies in the manual recording system using notebooks and Excel spreadsheets, which is prone to errors and data loss. Yet, structured offline mobile solutions for micro-scale fashion MSMEs with fragmented recording practices remain limited. This research aims to design and develop an Android-based stock management application utilizing a local Room Database for efficient and accurate digital recording. The study focuses on Gallery Muslim, a retail shop specializing in Muslim clothing and school uniforms. Data were collected through interviews, direct observation, and focus group discussions (FGD) with store owners and warehouse staff. Instruments included documentation of recording activities and analysis of feature requirements. The results demonstrate that the application accelerates the stock recording process by up to 50% compared to manual methods (based on initial simulations), enhances data accuracy, and enables offline access without an internet connection. The study concludes that this Android-based local application is highly suitable for MSMEs not yet integrated with online systems, offering a practical tool for small business owners to embark on digital transformation and improve operational efficiency.
Klasifikasi Tingkat Kepuasan Masyarakat terhadap Pelayanan Pembuatan KTP Elektronik di Dinas Dukcapil Semper Barat Menggunakan Metode Naïve Bayes Lestari, Dinny Amalia; Sugiyono, Sugiyono; Akbar, Yuma; Hidayat, Aditya Zakaria
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 6 No. 3 (2025): September
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63447/jimik.v6i3.1598

Abstract

Population administration plays an important role in Indonesia as it is involved in various activities at the government agency level. Based on data from 2020, the population in Jakarta reached 2,343,511 people. This indicates that the government in every region must provide the best service in managing population administration, especially in the issuance of electronic ID cards (e-KTP). However, various issues have been found that lead to public dissatisfaction, such as the lengthy service process, lack of information, and limited number of service personnel. Therefore, it is necessary to conduct an analysis of the level of public satisfaction to evaluate and improve service quality. This research aims to classify the level of satisfaction of the community regarding the service of e-KTP issuance. The object of this study is the community members who are applying for electronic ID cards at the Dukcapil Semper Barat. The method used in this research is a quantitative approach, with data collection through questionnaires distributed to 100 respondents. Data is obtained using questionnaires distributed to the public, and subsequently analyzed through classification performance evaluation processes. The results of this study indicate that the Naïve Bayes method is capable of classifying the level of public satisfaction with a fairly good accuracy rate. These findings are expected to serve as a reference for the Dukcapil in improving the quality of public services sustainably.
Optimasi Access Control List (ACL) Jaringan dalam Menangkal Akses Ilegal Jaringan Cisco Arif, Sulthan Cendikia; Surapati, Untung; Akbar, Yuma; Hidayat, Aditya Zakaria
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 6 No. 3 (2025): September
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63447/jimik.v6i3.1606

Abstract

This study examines how to block unauthorized access while keeping services available in an enterprise network. The approach combines Access Control Lists (ACLs) allow/deny rules on routers and Policy-Based Routing (PBR), which steers specific traffic without changing the main routing setup. The object of study is a lab simulation with four understandable parts: a central network (head office), an applications/services network, a provider/carrier network, and an external network (internet/partners). The method evaluates three scenarios: baseline, ACL, and ACL + PBR, in a virtual environment using straightforward measurements (ping, traceroute, and rule/route activity logs). Results show the internal subnet is closed in both directions as required; the legitimate path from the central network to the services network remains available and balanced via the provider network; there is no route leakage from the external network to unauthorized areas; and PBR successfully guides specific flows without disrupting the primary path. In conclusion, combining ACL + PBR effectively strengthens security while maintaining service availability, serving as a practical guide for multi-domain enterprise networks.
Automatic Purchase Order Classification Using SVM in POS System at Skus Mart Lestari, Sri; Nadip, Muhamad Zaeni; Akbar, Yuma; Hidayat, Aditya Zakaria; Aula, Raisah Fajri
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 2 (2025): AUGUST 2025
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i2.4564

Abstract

In retail business processes, decision-making regarding Purchase Order PO submissions often remains manual and subjective, creating risks that impede procurement efficiency. The study develops an automatic classification model to predict PO approval status using Support Vector Machine SVM algorithm integrated within Point of Sale POS systems. Historical purchase transaction data was obtained from SKUS Mart POS database containing 133 entries, including attributes such as item quantity, purchase price, previous stock levels, and total purchase amounts. The research applies CRISP-DM methodology, encompassing business understanding, data exploration, preprocessing normalization using StandardScaler, model training, evaluation, and deployment phases. The model was trained using linear kernel and validated through holdout technique with 80:20 ratio for training and testing. Test results demonstrate that the SVM model achieves 76.69% accuracy, 82.21% precision, 76.69% recall, and 78.51% F1-score. The model was implemented in a web-based POS system CodeIgniter 3 combined with Python scripts to generate automatic classifications displayed directly in the user interface. Although the model demonstrates adequate performance, the study has not compared its effectiveness against other machine learning algorithms such as Random Forest or K-Nearest Neighbor. These findings establish initial groundwork for machine learning integration to support decision automation in procurement systems.