Claim Missing Document
Check
Articles

Found 2 Documents
Search

Implementasi Visualisasi Log Server Web dengan ELK Stack: Analisis Kasus Log Akses pada Sistem Elena di Sekolah Tinggi Teknologi Terpadu Nurul Fikri Karmila, Hera; Saptono, Henry
Jurnal Informatika Terpadu Vol 10 No 1 (2024): Maret, 2024
Publisher : LPPM STT Terpadu Nurul Fikri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54914/jit.v10i1.764

Abstract

Nurul Fikri Integrated Technology College (STT NF) is a higher education institution that focuses on the field of information technology. STT NF has a web-based online learning system which is also called E-Learning by the name of Elena. Elena's system can be accessed online where the activity will be recorded by the server in the form of access log data. The access log data contains information on the user's IP, access time, requests sent, website browser used and others. Access logs contain useful information for monitoring server performance and more. However, Elena's system has problems in the form of access log data which is in text form which makes it difficult to read and the amount of data is large. Based on this, this study aims to provide a system that is used to store, process and visualize Elena STT NF system log access data automatically using a script The method used in this research is the development research method. The results obtained in this study are visualization in the form of important information from Elena's system log access data. In this research through several stages of research namely analysis, design, implementation, and testing. In the visualization test, the results were 100% and the test sending log data to Elasticsearch obtained 100% results, so that this research was implemented effectively.
Segmentasi Pelanggan Buah Segar dengan RFM dan Improved K-Means Berbasis Optimasi Centroid: Segmentation of Fresh Fruit Customers Using RFM and Improved K-Means Based on Centroid Optimization Rahayu, Agnes; Karmila, Hera; Triyono, Gandung
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 4 (2026): MALCOM October 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i4.2694

Abstract

Perkembangan teknologi informasi mendorong perusahaan untuk memanfaatkan data guna meningkatkan efektivitas strategi bisnis, termasuk dalam segmentasi pelanggan. Namun, pada kenyataannya, masih banyak perusahaan yang belum mengoptimalkan data transaksi secara maksimal. Pada perusahaan penjualan buah segar di Tangerang, terdapat sekitar 3.000 pelanggan terdaftar, namun hanya 748 diantaranya yang bertransaksi sepanjang tahun 2024. Fenomena ini mencerminkan urgensi strategi pemasaran untuk meningkatkan keterlibatan pelanggan dalam melakukan transaksi. Penelitian ini bertujuan menganalisis segmentasi pelanggan dengan pendekatan Recency, Frequency, and Monetary (RFM) serta algoritma K-Means standar dan Improved K-Means dengan optimasi inisialisasi centroid berbasis minimum variance dan global average distance untuk meningkatkan kualitas segmentasi pelanggan. Hasil pengujian metode elbow menunjukkan K=3 terbentuk sebagai cluster optimal. Hasil perbandingan menunjukkan bahwa Improved K-Means unggul dalam efisiensi waktu komputasi (0,0095 detik) dan kompaksi klaster yang lebih efektif dengan penurunan Sum of Squared Errors (SSE) sebesar 57,86%, Hasil Silhouette Score K-Means standar 0.565 dan Improved K-Means 0.564 relatif seimbang. Segmentasi yang dihasilkan mengidentifikasi tiga kelompok pelanggan: loyal bernilai tinggi, beraktivitas rendah, dan berisiko churn. Kontribusi penelitian ini terletak pada penerapan Improved K-Means pada data transaksi pelanggan serta interpretasi hasil segmentasi yang menjadi rekomendasi strategi pemasaran berbasis data dan lebih tepat sasaran, sehingga mendukung pertumbuhan bisnis yang berkelanjutan.