Article Per Year (5 Year)
p-Index From 2020 - 2025
0.61
P-Index
This Author published in this journals
All Journal Idealis : Indonesia Journal Information System J-Icon : Jurnal Komputer dan Informatika Jurnal Padamu Negeri
Bayu Satria Pratama
Program Studi Sistem Informasi, Universitas Budi Luhur
Computer Science & IT Decision Sciences, Operations Research & Management Education Other

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
KLASTERISASI DATA HASIL STUDI PELACAKAN TENTANG KARIR DAN PEKERJAAN LULUSAN PERGURUAN TINGGI MENGGUNAKAN ALGORITMA K-MEANS Sutrisno, Joko; Wibowo, Arief; Pratama, Bayu Satria
J-Icon : Jurnal Komputer dan Informatika Vol 11 No 2 (2023): Oktober 2023
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v11i2.12031

Abstract

Higher education has a responsibility to produce quality graduates. One indicator of the quality of graduates is the status of getting a job, the condition of the suitability of the field of work with the educational program pursued, and the waiting period to get the job. What is being done to find out these conditions is to conduct a tracer study for graduates. This study analyzes data from a college graduate tracking study about careers and jobs using a data mining clustering algorithm, namely K-Means. The results showed that the analysis of the tracking study data formed several graduate clusters with an evaluation value of the Davies-Bouldin Index (DBI) reaching 0.287 in the first trial and 0.291 in the second trial. The clusters formed consist of groups of graduates with status still needing to be working or currently working. The profile of graduates from each cluster can be identified in the form of a relatively short waiting period of less than six months to get a first job or a relatively slow waiting period of more than one year. Another cluster specification that is formed is about the profile of graduates with the level of compatibility between the education attained and the field of work carried out. The results of this study serve as feedback for study program managers to measure the quality of graduates and the improvements in the educational process that need to be made.
OPTIMALISASI PEMASARAN DIGITAL PADA PRODUK MINUMAN HERBAL POSBINDU DAHLIA INDAH Happy Egi Afriano; Nabillaputri Widiauliannisa; Septia Pratiwi; Dika Aisyah Veronika; Julian Bongsoikrama; Justin Bongsoikrama; Bayu Satria Pratama; Anastasia Putri Kristiani
Jurnal Padamu Negeri Vol. 2 No. 3 (2025): Juli : Jurnal Padamu Negeri (JPN)
Publisher : CV. Denasya Smart Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69714/rz0hw353

Abstract

This the community engagement aims to optimize the digital marketing of herbal beverage products developed by Posbindu Dahlia Indah as an effort to improve the competitiveness of local MSMEs. The program was conducted using a participatory approach through observation, interviews, training, and both pre-test and post-test evaluations. The results showed a significant increase in participant understanding, with an average improvement from 46.5% to 85.5%. The training covered digital marketing, branding strategies, social media management, and production and distribution planning. These findings indicate that digital marketing-based training contributes positively to enhancing the capacity of Posbindu cadres in managing their businesses. Challenges remain, such as limited production tools, non-eco-friendly packaging, and lack of product certification. However, opportunities exist in developing butterfly pea tea bags and expanding market reach through marketplace platforms and external partnerships. The study recommends strengthening digital strategies, packaging innovation, and certification processes as sustainable steps for the growth of local herbal businesses.
PERBANDINGAN K-MEANS DAN K-MEDOIDS DALAM PENGELOMPOKKAN TINGKAT KEJAHATAN PADA PROVINSI JAWA TENGAH Pratama, Bayu Satria; Purwanto, Gatot
IDEALIS : InDonEsiA journaL Information System Vol. 8 No. 2 (2025): Jurnal IDEALIS Juli 2025
Publisher : Universitas Budi Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36080/idealis.v8i2.3562

Abstract

Tindak kejahatan merupakan pelanggaran hukum dan norma sosial yang menimbulkan keresahan masyarakat serta mencerminkan dinamika sosial yang terus berkembang. Sepanjang tahun 2023, Provinsi Jawa Tengah mencatat 7.606 kasus kejahatan berdasarkan data dari Badan Pusat Statistik (BPS) Jawa Tengah pada website https://jateng.bps.go.id/id. Jenis kejahatan yang tercakup dalam data merupakan kejahatan konvensional, seperti pencurian, penganiayaan, dan penipuan. Penelitian ini bertujuan untuk mengelompokkan data kriminalitas menggunakan algoritma clustering K-Means dan K-Medoids guna mengidentifikasi pola kejahatan berdasarkan karakteristik wilayah. Data yang digunakan meliputi jumlah kejahatan, jumlah penduduk, dan jumlah penduduk tidak bekerja per kabupaten/kota, serta dua atribut turunan, yaitu Rasio_Kejahatan_Penduduk dan Rasio_Kejahatan_Tidak_Bekerja. Seluruh data numerik dinormalisasi menggunakan metode Min-Max agar memiliki skala yang sebanding. Pemilihan algoritma K-Means dan K-Medoids dilakukan karena keduanya merupakan metode partitional clustering yang banyak digunakan, namun memiliki pendekatan yang berbeda dalam menentukan pusat klaster, sehingga memberikan perbandingan hasil yang relevan. Evaluasi hasil klaster dilakukan dengan Davies-Bouldin Index (DBI) karena metrik ini mampu menilai validitas klaster berdasarkan tingkat kedekatan dan keterpisahan antar klaster. Klasterisasi dilakukan dengan jumlah klaster 3, 4, dan 5. Hasil evaluasi menunjukkan bahwa pembentukan 3 klaster adalah yang paling optimal, dengan nilai DBI terendah pada K-Means sebesar 0,082, sedikit lebih baik dibandingkan K-Medoids sebesar 0,084. Nilai DBI yang lebih rendah menunjukkan K-Means menghasilkan klaster yang lebih terpisah secara baik. Oleh karena itu, K-Means dipilih sebagai algoritma terbaik dalam penelitian ini. Hasil pengelompokan diharapkan menjadi dasar dalam pepersamaanan kebijakan.
Co-Authors Anastasia Putri Kristiani Arief Wibowo Dika Aisyah Veronika Happy Egi Afriano Joko Sutrisno Julian Bongsoikrama Justin Bongsoikrama Nabillaputri Widiauliannisa Purwanto, Gatot Septia Pratiwi