Jurnal Sistem Informasi Dan Informatika

Perancangan Sistem Informasi Terintegrasi untuk Manajemen Penjualan dan Inventaris guna Mendukung Efektivitas Operasional pada ArtTa Photo & Printing Pekanbaru

Nori Sahrun, Ikhwan Anshori, Sularno Sularno — Wed, 14 Jan 2026 11:25:59 +0700

This final project is entitled �Web-Based Sales and Stock Information System at Artta Photo & Printing�. Liyana Dita Shahibbah wrote this final project guided by Ikhwan Anshori, S.Kom., M.Kom. This research was prepared to overcome various problems in the sales process and inventory management that are still done manually. These problems include frequent errors in recording transactions, delays in checking stock, and inefficient report generation. The research method used is the Waterfall method, with stages namely Analysis, Design, Implementation, Unit Testing, System Integration and Testing, and Operation and Maintenance. The designed system provides features for managing product data, sales transactions, sales reports, and stock management automatically and in real-time. The results of this system development are expected to help Artta Photo & Printing in improving work efficiency, minimizing errors in recording, and providing more accurate and structured information to support decision making.

Jurnal Perancangan Sistem Informasi Pengolahan Data Nilai Siswa Berbasis Web Mobile Pada Sekolah Menengah Atas Negeri 2 Liwa

Pamuji Setiawan — Sat, 17 Jan 2026 15:09:30 +0700

Sistem Informasi Pengolahan Data Nilai Siswa Berbasis Web mobile merupakan suatu sistem yang memberikan informasi laporan keaktifan siswa secara online yang berupa laporan nilai serta informasi siswa yang bersangkutan dengan berbasiskan web, sehingga membantu kecepatan dan kualitas dalam penyampaian informasi. Permasalahan yang terjadi dalam pengolahan nilai raport di SMA N 2 Liwa saat ini masih bersifat konvensional, yaitu masih ditulis di buku raport dan leger nilai sehingga banyak waktu dan tenaga diperlukan untuk memproses tugas tersebut. Penelitian ini bertujuan untuk membangun suatu sistem informasi nilai yang mempermudah pengcekan, pencatatan dan laporan data nilai siswa yang terkomputerisasi. Selain itu dengan berbasiskan web mobile maka informasi data dapat diakses kapan saja. Aplikasi ini menggunakan multiuser yang terdiri admin dan siswa pada bagian login saat akan membuka aplikasi sehingga keamanan program ada. Sistem ini bekerja memasukan dan menyimpan data laporan nilai dan absensi serta menampilkan info dari sekolah tersebut sehingga lebih mudah mengetahui informasi yang akan disampaikan oleh pihak sekolah. Penelitian ini telah menghasilkan sebuah sistem pengolahan nilai yang membantu kerja dari para guru dan wali kelas dan dapat mempermudah pengguna untuk melakukan proses pengolahan nilai agar pengelolaan nilai dapat di olah secara efektif dan efisien, sehingga bisa langsung di akses serta informasi (pengumuman) dapat tersampaikan dengan baik. Selain itu antarmuka sistem diimplementasikan sesuai dengan tampilan raport yang sudah ada sehingga sistem dapat digunakan dengan mudah dan menghasilkan perhitungan nilai yang akurat.

Pemanfaatan Media Sosial untuk Branding (Studi Deskriptif pada Vamelania Laundry)

Hendrico Y — Mon, 26 Jan 2026 15:48:49 +0700

Building branding on social media isn't just about posting great photos or diligently creating Stories. It's about how the audience perceives the Vamelania Laundry brand among millions of other content. Think of social media as a digital living room where you can chat with potential customers. Branding is the promise and feeling people remember when they hear a business name. Branding is creating a persuasive message that effectively attracts consumers' attention. Based on these facts, Instagram isn't just a place to show off photos in the world of branding; it's a Visual Showcase and Connection Center. Due to its highly visual nature, this platform plays a crucial role in shaping audience perceptions of a brand. Vamelania Laundry, a pioneer in machine-based laundry services, offered by the piece and by the kilo in 2007, promoted its services using Instagram. The purpose of this study was to determine the branding activities carried out by Vamelania Laundry on its Instagram social media account and to determine the factors that led to Instagram being chosen as an active branding medium. This research method used was descriptive qualitative, which is a fact-finding method by collecting data in the form of words and images, not numbers. Therefore, this study will contain several data excerpts to illustrate the presentation of the report. Researchers concluded that Vamelania Laundry utilizes Instagram effectively, as evidenced by its diverse branding activities and its ability to utilize various available features.

Implementasi Protokol Redis Pub/Sub Menggunakan Python untuk Sistem Monitoring Suhu IoT Secara Real-Time

Hadadd Sammir, Khairil Hamdi, Isnardi . — Mon, 02 Feb 2026 13:23:16 +0700

This research implements the Redis Publish/Subscribe (Pub/Sub) mechanism using the Python programming language for real-time transmission of IoT temperature sensor data. The primary focus of this study is to address latency challenges in data distribution for logging and alerting system requirements. The system is designed with an architecture where temperature data is published to a Redis channel and simultaneously received by multiple subscribers. One subscriber unit is responsible for recording data into a database for historical analysis, while another unit validates temperature thresholds to trigger instant alerts upon detecting anomalies. Test results demonstrate that the use of Redis Pub/Sub effectively achieves decoupling between data senders and receivers, thereby enhancing system scalability. This architecture proves capable of distributing information with low latency and high efficiency. This study concludes that Redis Pub/Sub is a reliable solution for IoT monitoring systems that require rapid response and seamless data synchronization between monitoring functions and preventive actions.

Sistem Toko Online Berbasis PHP Menggunakan Framework Bootstrap: Desty�s Pastry

Muhammad Farhan Saputra, Anggi Hadi Wijaya, Ipriadi . — Fri, 13 Feb 2026 08:27:30 +0700

�Desty�s Pastry� previously relied on WhatsApp-based ordering and manual record-keeping, resulting in frequent order errors, limited market reach, and the absence of modern payment and notification features. This study aims to address these challenges by developing a web-based online store to improve operational efficiency and enhance customer experience. The system was built using the Waterfall development model, with requirements collected through interviews and direct observations. PHP 8.2, Bootstrap 5.3.5, and MySQL were used as core technologies, supported by Data Flow Diagrams and Entity Relationship Diagrams for system design. The resulting system provides key features including product catalog management, user authentication, shopping cart functionality, order processing, and an administrative dashboard, along with digital payment integration through QRIS. Black-box testing using Equivalence Partitioning showed that core functionalities such as registration, product selection, cart management, and order processing performed correctly with accurate data handling. Overall, the system successfully resolves initial operational issues and offers a scalable solution for SMEs adopting digital sales platforms.

Analisis Hierarchical Clustering untuk Segmentasi Pelanggan pada Dataset Mall Customers

Sat, 04 Apr 2026 00:00:00 +0700

Penelitian ini bertujuan untuk menganalisis segmentasi pelanggan menggunakan metode Hierarchical Clustering pada dataset Mall Customers. Tujuan utama penelitian adalah mengelompokkan pelanggan berdasarkan kemiripan Annual Income dan Spending Score. Metode penelitian meliputi preprocessing data menggunakan normalisasi Z-score, perhitungan jarak Euclidean, serta proses clustering menggunakan metode Ward linkage. Penentuan jumlah cluster optimal dilakukan dengan menggunakan beberapa metrik evaluasi seperti Silhouette Score, Calinski-Harabasz Index, dan Davies-Bouldin Index. Hasil penelitian menunjukkan bahwa jumlah cluster optimal adalah lima dengan performa clustering yang baik ditunjukkan oleh nilai Silhouette yang tinggi dan Davies-Bouldin yang rendah. Setiap cluster merepresentasikan segmen pelanggan yang berbeda seperti pelanggan dengan pendapatan tinggi dan belanja tinggi maupun rendah. Hasil ini dapat digunakan sebagai dasar strategi pemasaran yang lebih efektif.

Penerapan Random Forest untuk Klasifikasi Diagnosis Kanker Payudara Berbasis Dataset WBCD

Sun, 12 Apr 2026 00:00:00 +0700

Breast cancer is one of the most critical global health challenges, with Indonesia recording 66,271 new cases in 2022 according to GLOBOCAN data published by the International Agency for Research on Cancer (IARC/WHO). Early and accurate detection is essential to improving patient survival rates, yet conventional diagnosis remains time-consuming and dependent on expert availability. This study implements the Random Forest algorithm to classify breast cancer diagnosis using the Wisconsin Breast Cancer Diagnostic (WBCD) dataset from the UCI Machine Learning Repository. The dataset consists of 569 samples with 30 numerical features extracted from fine-needle aspirate (FNA) cell images, labeled as benign or malignant. Data preprocessing involved removing non-predictive columns, converting categorical labels to binary format, handling outliers using IQR Clipping, and applying StandardScaler normalization. The dataset was split into 80% training and 20% testing using stratified splitting, with the Random Forest Classifier configured using 100 decision trees and class_weight=balanced to handle class imbalance. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics alongside confusion matrix analysis and 5-Fold Stratified Cross Validation. The model achieved 97.37% accuracy on the test set, with zero False Positive predictions, meaning no benign patient was misdiagnosed as malignant. Cross-validation confirmed generalization ability with a mean accuracy of 96.31%, indicating no overfitting. Feature importance analysis identified area_worst, concave points_worst, and perimeter_worst as the most dominant features, consistent with the clinical morphological characteristics of malignant cancer cells. These findings demonstrate the strong potential of Random Forest as a reliable and interpretable tool for supporting breast cancer diagnosis.

Penerapan Metode Agglomerative Clustering Untuk Segmentasi Data Dalam Lingkungan Big Data

Wed, 15 Apr 2026 18:02:42 +0700

The exponential growth of data in the digital era has increased the need for analytical methods capable of handling Big Data characteristics. This study examines the application of Agglomerative Hierarchical Clustering (AHC) for data segmentation using two datasets: (1) an Iris dataset of 24 samples with 8 morphological attributes, and (2) an e-commerce transaction dataset of 10 customer records. Ward linkage was selected based on literature evidence of its superiority. Results on the Iris dataset yielded 3 optimal clusters with a Silhouette Score of 0.4196 and an Adjusted Rand Index of 0.3635, achieving 70.83% classification accuracy. In the e-commerce dataset, three customer segments were formed: premium, middle-tier, and passive customers. These findings confirm AHC as an effective multidimensional data segmentation method.

Analisis Segmentasi Kedisiplinan Karyawan Berdasarkan Data Absensi Menggunakan Algoritma K-Means Clustering

Steffany Marcellia Witanto, Wahyu Syaifullah Jauharis Saputra — Tue, 16 Jun 2026 16:08:21 +0700

Data absensi karyawan merupakan sumber informasi penting untuk menilai tingkat kedisiplinan dan pola kehadiran karyawan dalam suatu perusahaan. Namun, data absensi yang tersimpan dalam jumlah besar sering kali belum dimanfaatkan secara optimal untuk mendukung pengambilan keputusan bagi perusahaan. Penelitian ini bertujuan untuk mengelompokkan karyawan berdasarkan pola absensi menggunakan metode K-Means Clustering. Variabel yang digunakan meliputi total menit keterlambatan, total melakukan absensi, serta status kehadiran seperti duty, leave, sick, dan WFO. Tahapan penelitian terdiri dari pengumpulan data, preprocessing data, analisis korelasi, transformasi data, penentuan jumlah cluster, proses clustering, serta evaluasi model. Hasil penelitian ini menunjukkan bahwa K-Means menghasilkan 3 cluster dengan nilai Silhouette Score sebesar 0,414. Nilai tersebut menunjukkan bahwa struktur cluster cukup lemah namun layak, serta mampu menggambarkan perbedaan karakteristik kedisiplinan serta pola kehadiran karyawan. Hasil clustering ini dapat digunakan sebagai dasar evaluasi sumber daya manusia secara lebih objektif.

Perancangan Sistem Customer Intelligence Berbasis Fuzzy C-Means dan Pemetaan Point of Interest (POI) untuk Mendukung Strategi Layanan Perusahaan Telekomunikasi

Ni Luh Ayu Nariswari Dewi — Sat, 20 Jun 2026 21:37:12 +0700

This study aims to design and develop a web-based Customer Intelligence system that integrates customer segmentation, customer value prediction, and location mapping into a unified platform. The Fuzzy C-Means algorithm is used for customer segmentation based on behavioral characteristics, while the Decision Tree Regressor is applied to predict Average Revenue per User (ARPU). In addition, the system incorporates Point of Interest (POI) visualization to support location-based analysis. The results show that the clustering model successfully identifies three to four customer segments with distinct characteristics based on ARPU, service usage, and customer loyalty. The prediction model achieves a good performance with an R² value of 0.8905 on the testing data. The system is also able to automatically generate service recommendations based on customer segmentation results. Therefore, the proposed system can assist telecommunication companies in formulating more effective and data-driven service strategies.