cover
Contact Name
Sarida Sirait
Contact Email
saridasrt@gmail.com
Phone
+6281319494217
Journal Mail Official
saridasrt@gmail.com
Editorial Address
Jl. Sriwijya No. 9 C-E Pematangsiantar, Sumatera Utara
Location
Kota pematangsiantar,
Sumatera utara
INDONESIA
Jurnal Tekinkom (Teknik Informasi dan Komputer)
ISSN : 26211556     EISSN : 26213079     DOI : https://doi.org/10.37600/tekinkom
Core Subject : Science,
Jurnal TEKINKOM merupakan jurnal yang dimaksudkan sebagai media terbitan kajian ilmiah hasil penelitian, pemikiran dan kajian analisis-kritis mengenai isu Ilmu - ilmu komputer dan sistem informasi, seperti : Pemrograman Jaringan, Jaringan Komputer, Teknik Komputer, Ilmu Komputer/Informatika, Sistem Informasi, dan Multi Disiplin Penunjang Domain Penelitian Komputasi, Sistem dan Teknologi Informasi dan Komunikasi, dan lain-lain yang terkait. Artikel ilmiah dimaksud berupa kajian teori (theoritical review) dan kajian empiris dari ilmu terkait, yang dapat dipertanggungjawabkan serta disebarluaskan secara nasional maupun internasional.
Articles 407 Documents
STACKING ENSEMBLE, XGBOOST DAN SMOTE UNTUK EFISIENSI ENERGI PADA FRAUD CREDIT CARD Bayuaji, Hibatullah Zamzam Tegar; Prasetiyo, Budi
Jurnal Teknik Informasi dan Komputer (Tekinkom) Vol 8 No 1 (2025)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v8i1.2409

Abstract

Extreme class imbalance in credit card fraud detection datasets often leads machine learning models to fail in recognizing minority fraud cases. This study proposes a Stacking Ensemble approach combined with Synthetic Minority Oversampling Technique (SMOTE) and SMOTE-Tomek Links, employing XGBoost, LightGBM, and Random Forest as base learners and XGBoost as a meta-learner. Using the Kaggle Credit Card Fraud Detection dataset (class ratio 1:492), the method was evaluated with Recall, F1-Score, AUC-PR, and AUC-ROC, while CodeCarbon was integrated to measure energy consumption and carbon emissions during model training. Experimental results show that the proposed ensemble improves Recall of fraud detection by up to 6% compared to single models, achieves stable F1-Scores of 0.92 (SMOTE) and 0.91 (SMOTE-Tomek), and records an AUC-PR above 0.90. Furthermore, CodeCarbon tracking indicates that SMOTE models produce slightly lower carbon emissions (0.62 gCO₂) than SMOTE-Tomek (0.68 gCO₂), highlighting a trade-off between detection accuracy and energy efficiency. These findings emphasize that integrating ensemble learning with oversampling techniques not only enhances fraud detection performance but also provides transparent insights into the environmental impact of machine learning models.
PERANCANGAN DESIGN UI/UX WEBSITE HOUSE OF NEGATIVE MENGGUNAKAN METODE DESIGN THINKING Putra, Gilang Adi; Utami, Putri Yuli; Istikoma, Istikoma
Jurnal Teknik Informasi dan Komputer (Tekinkom) Vol 8 No 1 (2025)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v8i1.2347

Abstract

House of Negative is an independent music label established in 2019, engaged in the production and distribution of diverse musical works. This study focuses on the design of the user interface (UI) and user experience (UX) of the House of Negative website using the Design Thinking approach. The objective is to develop an interface that is both intuitive and user-friendly, thereby improving user interaction with the label and its associated content. The stages of Design Thinking were implemented to identify user needs and formulate appropriate design solutions. The resulting prototype was evaluated using the System Usability Scale (SUS), which produced a usability score of 87.25, classified in the “excellent” category and exceeding the standard of the previous application. These results indicate that the Design Thinking methodology is effective in generating UI solutions that are functional, relevant, and user-centered. The intended users of the website include musicians and the general public; the former is facilitated in managing their musical portfolios and audience engagement, while the latter are provided with a platform for discovering new music and interacting within the broader music community.
PEMANFAATAN E-COMMERCE SEBAGAI BENTUK TRANSFORMASI DIGITAL PENJUALAN BAGI PELAKU UMKM Triesia, Diah; Putri, Intan; Dwipa, Ruswa; Rizki, Rani Ria
Jurnal Teknik Informasi dan Komputer (Tekinkom) Vol 8 No 1 (2025)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v8i1.2384

Abstract

This research explores the utilization of e-commerce as a form of digital transformation in sales among Micro, Small, and Medium Enterprises (MSMEs) in Palembang City. The rapid development of digital technology has significantly influenced the business sector, particularly MSMEs that are required to adapt in order to stay competitive. The study aims to analyze how MSME actors in Palembang adopt e-commerce platforms to improve business performance, expand market reach, and enhance customer engagement. Using a qualitative descriptive approach, data were collected through in-depth interviews with selected MSME owners and analyzed using thematic analysis. The findings reveal that although awareness and adoption of e-commerce among MSMEs are increasing, many still face challenges related to digital skills, infrastructure, and consistent online marketing strategies. The results indicate that e-commerce adoption has contributed to an average sales increase of 25–40%, reduced operational costs, and enabled penetration into new market segments outside the local area. The discussion highlights that the successful integration of e-commerce requires not only technical readiness but also continuous digital literacy, promotional consistency, and supportive government policies. In conclusion, digital transformation through e-commerce is not only a technological shift but also a strategic necessity for MSMEs in Palembang to sustain competitiveness, improve operational efficiency, and achieve long-term business growth in the digital economy era.
PENERAPAN DATA MINING MENGGUNAKAN NAÏVE BAYES UNTUK OPTIMALISASI PENJUALAN SPAREPART MOTOR Alifyaa, Adhyndha; Tatuhey, Emy Lenora; Hasan, Patmawati
Jurnal Teknik Informasi dan Komputer (Tekinkom) Vol 8 No 1 (2025)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v8i1.2257

Abstract

This study focuses on the challenges of inventory management and marketing strategies faced by PWT-Part Timika Wholesale Store, which are often hampered by delivery delays. To overcome this, a data mining method using the Naïve Bayes algorithm was applied to optimize motorcycle spare parts sales. The objective of this study is to optimize motorcycle spare part sales by analyzing sales data and classifying spare parts based on their brands. The research approach used is a quantitative method involving the Knowledge Discovery in Database (KDD) process, which involves processing 1,010 sales data points from 2021 to 2023. After preprocessing, 567 data points were used, with 80% (454 data points) allocated for training and 20% (113 data points) for testing using the Weka application. The test results showed that the Naïve Bayes model had good classification performance, with an accuracy of 82.30%, precision of 81.8%, and recall of 82.3%. The conclusion of this study confirms that the Naïve Bayes algorithm is capable of classifying parts based on brand, not just the categories “popular” or “unpopular.” This enables PWT-Part to identify customer preferences more specifically, design more targeted marketing strategies, and optimize inventory.
PERANCANGAN UI/UX APLIKASI PENCARI PEKERJAAN FREELANCE MENGGUNAKAN METODE DESIGN THINKING Sadid, Moh Naufal; Prasetiyo, Budi
Jurnal Teknik Informasi dan Komputer (Tekinkom) Vol 8 No 1 (2025)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v8i1.2395

Abstract

The global shift in work patterns over the past decade has significantly increased the number of freelancers, including in Indonesia, where nearly one-third of the 145.79 million workforce engage in freelance work. This trend is driven by limited formal job opportunities, high qualification requirements, lack of work experience among job seekers, and restricted access to job vacancy information. Freelancing has become an adaptive alternative amid high unemployment rates among the productive-age population. This situation highlights the need for innovative digital platforms that connect freelancers with the job market through optimal user interface (UI) and user experience (UX) design. This study applies the design thinking method to develop the UI/UX of a freelance job search application called Jobble, addressing freelancers’ needs such as interest-based job searches, automatic CV generation, direct client communication, and skill-enhancing training. The resulting UI/UX design facilitates access to relevant job opportunities. A usability test using the System Usability Scale (SUS) achieved a score of 81.53, categorized as “Good,” indicating that Jobble’s UI/UX design meets user needs and has strong potential as a digital solution for freelancers in Indonesia.
PENERAPAN SYSTEM USABILITY SCALE DAN USER-CENTERED DESIGN PADA PENGUJIAN PLATFORM PEMBELAJARAN DIGITAL Dewinta, Virgie Melky; Ikhwani, Muhammad; Ula, Mutamimmul
Jurnal Teknik Informasi dan Komputer (Tekinkom) Vol 8 No 1 (2025)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v8i1.2268

Abstract

The digital transformation in education has accelerated the use of online learning platforms such as Ruangguru. However, the quality of the user interface (UI) plays a crucial role in determining user comfort and application effectiveness. This study aims to evaluate and improve the interface design of the Ruangguru application by applying the System Usability Scale (SUS) method and the User-Centered Design (UCD) approach. SUS was used to measure usability based on user perceptions, while UCD guided the redesign process to align with the needs and characteristics of users from elementary, junior high, and senior high school levels. Initial testing showed an average SUS score of 35, which falls into the Not Acceptable category. After redesigning the interface using UCD principles, the follow-up test showed an improved SUS score of 57, categorized as Marginal Usability. This increase reflects a notable improvement in user experience, although it has not yet reached the optimal level. Therefore, the implementation of SUS and UCD proved effective in identifying design issues and offering solutions tailored to user needs. The findings provide a solid foundation for further development of more user-friendly and inclusive digital learning platforms.
KOMPARASI PERFORMA INFRASTRUKTUR WORDPRESS PADA DIGITALOCEAN (CLOUD) DAN VMWARE WORKSTATION (ON-PREMISES) Ahkam, Mizanul; Bakar, Abu; Kurniawati, Kurniawati
Jurnal Teknik Informasi dan Komputer (Tekinkom) Vol 8 No 1 (2025)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v8i1.2398

Abstract

This study evaluates the performance of WordPress infrastructure on two different hosting platforms: DigitalOcean VPS (cloud) and VMware Workstation (on-premises). The research aims to compare key performance metrics including Time to First Byte (TTFB), Largest Contentful Paint (LCP), Fully Loaded Time, Cumulative Layout Shift (CLS), and overall page speed score. Identical WordPress installations (version 6.8.1, Twenty Twenty-Five theme, no caching plugins) were deployed on both platforms using Debian 12 and LAMP stack. Performance was tested using SpeedVitals (Jakarta, desktop), WebPageTest (Singapore, Chrome), and Google PageSpeed Insights (mobile). Results show that DigitalOcean significantly outperforms the local VMware setup: TTFB was 128 ms versus 256 ms, LCP was 0.5 seconds versus 1.2 seconds, and the performance score reached 100 compared to 87. The superior performance is attributed to faster network connectivity, SSD storage, and optimized cloud infrastructure. In contrast, the VMware setup experienced higher latency due to local internet constraints. The study concludes that DigitalOcean is more suitable for production environments requiring high performance, while VMware Workstation remains ideal for local development and testing. These findings provide practical guidance for developers and administrators in selecting appropriate hosting platforms based on performance needs and resource constraints.