Claim Missing Document
Check
Articles

Found 30 Documents
Search

Unveiling Hidden Customer Segments in E-Commerce Using DBSCAN Clustering on Demographic and Behavioral Insights Aglasia, Adimas; Agus, Isnandar
International Journal for Applied Information Management Vol. 4 No. 3 (2024): Regular Issue: September 2024
Publisher : Bright Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/ijaim.v4i3.85

Abstract

Customer segmentation is a crucial process in e-commerce that allows businesses to tailor their marketing strategies to specific customer groups. This research applies the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm to segment customers based on their demographic and behavioral data. The dataset used includes variables such as age, annual income, total spending, and campaign engagement, which are essential for identifying meaningful patterns within the customer base. The DBSCAN algorithm was chosen due to its ability to detect clusters of arbitrary shapes and handle noise, making it ideal for complex e-commerce datasets. The analysis identified one dominant customer segment, with a small portion of the data labeled as noise, indicating that the majority of customers exhibit similar behaviors. However, the results also highlight the challenge of parameter selection for DBSCAN, as the clustering outcome was sensitive to the chosen values of ε (epsilon) and MinPts. The segmentation revealed valuable insights, such as the fact that most customers share similar characteristics in terms of spending habits and engagement, yet a few outliers exist who do not align with these patterns. These findings provide a foundation for businesses to develop targeted marketing strategies based on customer segmentation. Despite the promising results, the study acknowledges limitations in the segmentation process, particularly with the influence of outliers and the need for further tuning of the algorithm's parameters. Future research could explore hybrid clustering models that combine DBSCAN with other techniques, as well as incorporating additional behavioral features for more refined segmentation. The insights gained from this research can guide businesses in crafting personalized marketing campaigns that cater to distinct customer segments.
Model Pelacakan Objek Berbasis YOLO-OCSort Untuk Estimasi Kepadatan Lalu Lintas Linda, Deppi; N; Agus, Isnandar
Jurnal Informatika Vol 25 No 1 (2025): Jurnal Informatika
Publisher : Institut Informatika Dan Bisnis Darmajaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30873/jurnalinformatika.v25i3

Abstract

Accurate traffic density estimation is a crucial component in intelligent transportation systems for optimizing urban trafficmanagement. This research develops an object tracking model based on YOLOv8 and Online Clustering SORT (OCSort) integration for realtime trafficdensity estimation. YOLOv8 is used as a highaccuracy object detector, while OCSort implements a tracking algorithm with observationcentric association approach to overcome conventional tracking limitations in handling nonlinear motion and temporal occlusion. Comprehensive evaluation was conducted using MOT17FRCNN benchmark Dataset for tracking performance measurement and UADETRAC Dataset subset for computational performance analysis. The system was tested on Intel Core i7 Generation 13 hardware, 32 GB RAM, and NVIDIA GeForce RTX 3060 12 GB VRAM. Evaluation results show MOTA of 0.4910, MOTP 0.9072, and IDF1 0.6702 with very low identity switches (7 occurrences) and 65 fragmentations. Comparison with stateoftheart methods using 2001 frames demonstrates significant YOLOOCSort superiority in computational efficiency with best processing time of 118.01 seconds, outperforming ByteTrack (146.98s), BoTSORT (161.91s), and DeepSORT (152.33s). The system achieves endtoend FPS of 17.0, model processing time 33.8 ms per frame, and detects average 20.1 objects per frame with confidence score 0.608. Statistical analysis with 95% confidence interval confirms consistency and reliability of evaluation results. The contribution of this research is empirical validation of YOLOv8OCSort integration effectiveness that produces optimal balance between tracking accuracy and computational efficiency for realtime traffic cmonitoring applications.
Pengujian Blackbox pada Sistem Informasi Komunitas Pecinta Kucing di Bandar Lampung Fikri, Ruki Rizal Nul; Indera, Indera; Rahardi, Agus; Agus, Isnandar
TEKNIKA Vol. 18 No. 1 (2024): Teknika Januari - Juni 2024
Publisher : Politeknik Negeri Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.10513105

Abstract

Penelitian ini merespon dengan pertumbuhan minat komunitas pecinta kucing di Bandar Lampung dengan menelusuri dan mengevaluasi keandalan Sistem Informasi Forum Komunitas Pecinta Kucing melalui pendekatan blackbox testing. Fokus penelitian ditujukan untuk mengamati fungsionalitas sistem, untuk menemukan kekurangan dari sistem yang sebelumnya tidak diketahui oleh komunitas. Melalui penerapan metode blackbox testing, kinerja sistem dievaluasi dengan skenario penggunaan uji fungsional. Hasil pengujian akan mengungkap sejumlah aspek terkait peforma sistem, serta menemukan bagian masalah yang dapat disarankan untuk diperbaiki. Dari 12 skenario pengujian yang digunakan, 75% pengujian menghasilkan hasil yang valid atau lulus uji, sementara 25% menghasilkan hasil yang tidak valid atau tidak valid, hal ini menandakan perlunya perbaikan dan tindak lanjut untuk meningkatkan pengalaman pengguna sistem. Dari penelitian ini dapat disimpulkan bahwa pengujian blackbox pada Sistem Informasi Komunitas Pecinta Kucing di Bandar Lampung memiliki peran yang sangat penting dalam menemukan masalah pada sistem tersebut, sehingga akan meningkatkan kewaspadaan pada komunitas pada sistem yang telah dibangun serta untuk pengembangan sistem pada masa yang akan datang.
Transformasi Bisnis di Era Digital: Analisis Sistematis Terhadap E-Bisnis di Indonesia Pada Konteks UMKM Septiadi, Bayu; Agus, Isnandar
Journal of Digital Literacy and Volunteering Vol. 2 No. 1 (2024): January
Publisher : Puslitbang Akademi Relawan TIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57119/litdig.v2i1.80

Abstract

Business transformation in the digital era and systematic analysis of e-business in Indonesia, especially in the context of UMKM (Micro, Small and Medium Enterprises). The growth of e-business in Indonesia is related to technological advances and changes in consumer behavior. This article aims to provide a comprehensive understanding of developments, challenges and potential solutions to support UMKM business transformation in the digital era. Some of the topics studied include the role of e-business in the transformation of UMKM in Indonesia, challenges in adopting e-business technology, effective strategies for encouraging e-business adoption among UMKM, and the impact of business transformation through e-business on local economic growth. The research method uses a systematic literature review (SLR) approach to investigate and analyze relevant literature. The findings from this research show that e-business has an important role in the development of UMKM in Indonesia, but UMKM still face challenges in adopting digital technology. Therefore, an effective strategy is needed to encourage the adoption of e-business among UMKM and the impact of business transformation through e-business can make a positive contribution to local economic growth. It is hoped that this research can support the development and sustainability of UMKM in Indonesia in this digital era.
STRATEGI KOMUNIKASI DIGITAL POLRI DALAM MEMBANGUN REPUTASI POLDA LAMPUNG DI MEDIA SOSIAL Agus, Isnandar; Rohani; Wijaya, Muhammad Andri; Suhardi, Tri
Jurnal Bisnis Darmajaya Vol. 11 No. 2 (2025): Jurnal Bisnis Darmajaya
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat (LPPM)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30873/jurnalbisnis.v11i2.1153

Abstract

The dynamics of public reputation and trust in the Indonesian National Police are influenced by news coverage and social media discourse. Yet, comprehensive studies on the strategic communication practices of the Public Relations Bureau of the Lampung Regional Police in strengthening institutional reputation in digital spaces remain limited. This study aims to analyze the digital communication strategies of Bidang Humas Polda Lampung and to evaluate its social media management in efforts to build, maintain, and strengthen institutional reputation. Using a qualitative case study design, the research covers the 2022–2024 period. Data were collected through semi-structured interviews, observation, and content documentation from official channels (Instagram, TikTok, Facebook, X, and the official website), with source and method triangulation. The findings indicate targeted digital communication management through systematic content planning, cross-platform message adaptation, coordinated issue response and clarification, and responsive, ethical two-way interaction. The study also maps three key aspects: the workflow of public communication management, cross-platform channel utilization, and public interaction patterns associated with reputation. The study recommends strengthening personnel capacity, refining operational guidelines for issue management, and conducting periodic evaluations using platform analytics to ensure that digital communication strategies are implemented consistently and sustainably.  
The Effect of Regulations and Policies on the Development of E-Business in Indonesia Heri Nurdiyanto; Muhammad Said Hasibuan; Isnandar Agus; faurani santi singagerda
Journal of Research in Social Science and Humanities Vol 4, No 2 (2024)
Publisher : Utan Kayu Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47679/jrssh.v4i2.143

Abstract

This paper examines the impact of regulations and policies on the development of e-business in Indonesia. As e-business becomes increasingly integral to the economy, understanding the regulatory environment is crucial for stakeholders, including policymakers, business owners, and consumers. The study explores the current regulatory framework governing e-business in Indonesia, identifying key policies that influence its growth and development. Through qualitative analysis of government regulations, industry reports, and expert interviews, the paper highlights both the supportive and restrictive aspects of these regulations. Findings indicate that while certain policies, such as tax incentives and infrastructure investments, have fostered e-business growth, others, including stringent data protection laws and complex compliance requirements, pose challenges. The research underscores the need for a balanced regulatory approach that promotes innovation while ensuring consumer protection and fair competition. Recommendations are provided for policymakers to enhance the regulatory landscape, suggesting measures such as streamlined compliance processes, enhanced digital literacy programs, and increased collaboration between government and industry stakeholders. Ultimately, this paper aims to contribute to the discourse on how regulations can be optimized to support the sustainable growth of e-business in Indonesia, aligning with broader economic goals and technological advancements.
STRATEGI TRANSFORMASI DIGITAL UNTUK PENGUATAN BRANDING DAN EKSPANSI PASAR EKSPOR PRODUK BRIKET ARANG KELAPA: STUDI KASUS PT HOJAYA GROUP INTERNATIONAL (HOOCOCO) Hafina Oktaviani; Anggalia Wibasuri; Isnandar Agus
Derivatif : Jurnal Manajemen Vol. 20 No. 1 (2026): April
Publisher : Universitas Muhammadiyah Metro Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24127/jm.v20i1.2857

Abstract

Menghadapi persaingan global yang semakin pesat di dunia digital, PT Hojaya Group International (Hoococo), produsen briket arang kelapa asal Indonesia, perlu menerapkan strategi transformasi digital untuk memperkuat citra merek dan memperluas penetrasi pasar ekspor. Penelitian ini bertujuan untuk merumuskan strategi transformasi digital yang efektif dalam meningkatkan visibilitas merek Hoococo di pasar global, serta menganalisis dampaknya terhadap perluasan jangkauan pasar ekspor produk briket arang kelapa. Penelitian ini menggunakan pendekatan studi kasus kualitatif. Sumber data utama dalam penelitian ini adalah wawancara mendalam dengan tiga informan kunci yang dipilih secara purposive. Informan tersebut terdiri dari Staf Pemasaran Digital Hoococo, pelanggan ekspor, dan pihak manajemen perusahaan. Kriteria pemilihan informan didasarkan pada peran mereka yang relevan dalam proses transformasi digital dan pengaruhnya terhadap strategi pemasaran ekspor. Data yang dikumpulkan dianalisis menggunakan pendekatan tematik untuk mengidentifikasi pola dan temuan kunci. Hoococo telah mengembangkan situs web resmi (hoococo.com) yang berfungsi sebagai etalase utama bagi produk mereka. Tim pemasaran digital secara rutin memperbarui konten blog, dengan artikel edukasi bulanan yang menunjukkan keunggulan briket arang kelapa Hoococo dibandingkan produk arang lainnya. Artikel-artikel ini terbukti efektif dalam menarik perhatian pelanggan internasional, sebagaimana tercermin dari peningkatan traffic website sebesar 30% dalam tiga bulan terakhir. Berdasarkan temuan penelitian, Hoococo disarankan untuk terus memperkaya konten digital dengan menambahkan video produk, profil perusahaan, dan testimonial pelanggan. Selain itu, untuk meningkatkan efisiensi proses pemasaran dan distribusi, Hoococo sebaiknya mengintegrasikan sistem manajemen pesanan dengan platform digital mereka. Penggunaan alat analitik web yang lebih canggih juga akan membantu dalam memahami pola perilaku pelanggan dan mengoptimalkan konversi dari prospek menjadi pembeli.Kata kunci: transformasi digital; branding; ekspansi pasar ekspor; briket arang kelapa; pemasaran digital
Perancangan Virtual Reality Tour Sebagai Media Promosi Untuk Meningkatkan Daya Saing Sekolah Isnandar Agus; Aulia Sindi Regita Pramesti
TEKNIKA Vol. 20 No. 1 (2026): Teknika Januari 2026
Publisher : Politeknik Negeri Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.17641240

Abstract

SMK Negeri 4 Metro menghadapi tantangan dalam menarik minat calon siswa akibat keterbatasan media promosi digital dan lokasi sekolah yang kurang strategis. Penelitian ini bertujuan untuk merancang media promosi interaktif berbasis Virtual Reality (VR) yang mampu meningkatkan daya saing dan citra sekolah melalui pengalaman eksplorasi virtual yang imersif. Metode yang digunakan adalah Multimedia Development Life Cycle (MDLC) yang meliputi tahapan konsep, perancangan, pengumpulan bahan, pembuatan, pengujian, dan distribusi. Hasil penelitian berupa Virtual Reality Tour interaktif yang menampilkan lingkungan, fasilitas, dan program keahlian sekolah dalam bentuk tampilan 360°. Berdasarkan uji black box dan pengujian pengguna, seluruh fitur berjalan dengan baik, dengan aspek kemudahan akses memperoleh penilaian tertinggi. Penerapan media ini memberikan dampak positif berupa peningkatan efektivitas promosi sekolah, perluasan jangkauan informasi, serta penguatan citra SMK Negeri 4 Metro sebagai lembaga pendidikan vokasi yang adaptif terhadap perkembangan teknologi digital.
Pengembangan Aplikasi Interaktif Pengenalan Pakaian Adat Indonesia Berbasis Android Untuk SD Isnandar Agus; Rifqa Hanum Fadillah
TEKNIKA Vol. 20 No. 1 (2026): Teknika Januari 2026
Publisher : Politeknik Negeri Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.17641237

Abstract

Meningkatnya kebutuhan akan media pembelajaran yang menarik dan interaktif untuk mengenalkan kebudayaan nasional kepada siswa sekolah dasar menjadi latar belakang penelitian ini. Proses pembelajaran mengenai pakaian adat Indonesia yang selama ini disampaikan melalui buku teks dinilai kurang efektif dalam menarik minat belajar siswa. Penelitian ini bertujuan mengembangkan aplikasi pembelajaran interaktif berbasis Android untuk membantu siswa mengenal pakaian adat Indonesia secara visual dan menyenangkan. Aplikasi dikembangkan menggunakan Construct 2 dengan metode Multimedia Development Life Cycle (MDLC) yang terdiri dari enam tahap, yaitu konsep, desain, pengumpulan materi, perakitan, pengujian, dan distribusi. Hasil pengujian sistem menggunakan metode Black Box menunjukkan seluruh fitur aplikasi berfungsi dengan baik tanpa kesalahan. Selain itu, hasil pre-test dan post-test menunjukkan peningkatan rata-rata nilai sebesar 13 poin setelah penggunaan aplikasi. Hasil tersebut membuktikan bahwa aplikasi ini efektif sebagai media pembelajaran tambahan karena mampu meningkatkan motivasi, pemahaman, serta keterlibatan siswa dalam mengenal keragaman budaya Indonesia melalui tampilan digital interaktif.
WEB-BASED RESEARCH ARTICLE CLASSIFICATION USING THE RANDOM FOREST ALGORITHM Fiqqi Ahludzikri; Riko Herwanto; Abdul Aziz RZ; Isnandar Agus; Suhendro Yusuf Irianto
Jurnal Ilmu Siber dan Teknologi Digital Vol 4 No 1 (2025): November
Publisher : Penerbit Goodwood

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35912/jisted.v4i1.5547

Abstract

Purpose: This study aims to develop a web-based system that classifies research articles using the Random Forest algorithm to address mismatches between article content and journal scope. Methodology/approach: The research employed the SDLC Waterfall model, with data sourced from 560 articles published by Goodwood Publishing (2019–2024) across four categories. Text preprocessing included case folding, stopword removal, stemming, and tokenization, with TF-IDF applied for feature extraction. Random Forest was trained with 80% training data and 20% testing data. Results/findings: The model achieved 91% accuracy, with high precision and recall across all categories. The system was successfully implemented as a web-based application, providing instant classification and journal recommendations. Limitations: The dataset was limited to one publisher and only Random Forest was applied, which may restrict the generalizability of findings. Contribution: This study contributes to the application of machine learning in scholarly publishing, offering a practical solution for editors to streamline article selection and improve efficiency.