Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : CICES (Cyberpreneurship Innovative and Creative Exact and Social Science)

Implementasi Arsitektur Mikroservis dan Orkestrasi Kubernetes dengan Paradigma DDD pada Website Freelancing Farhana, Hafi Ihza; Mumpuni, Retno; Ali Akbar, Fawwaz
CICES (Cyberpreneurship Innovative and Creative Exact and Social Science) Vol 11 No 1 (2025): CICES
Publisher : UNIVERSITAS RAHARJA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/cices.v11i1.3496

Abstract

The rapid development of the digital era triggered by COVID-19 has changed the way people earn income, with more and more people turning to freelance work. M-Knows Consulting responded to this change by creating a website-based freelance platform, designed to be a place for Indonesian freelancers to develop their careers. Given the complexity of the system and the high interaction of various users, a more modular development is needed to increase efficiency, especially in handling diverse project challenges. Therefore, a microservice architecture was chosen as a more appropriate solution than a monolithic architecture. The design of this microservice architecture involves several important steps, including the application of the Domain-Driven Design (DDD) paradigm with the principle of bounded context to clearly separate business domains and implement a multi-database approach that suits the specific needs of each service. The deployment process will be carried out using Kubernetes to manage the workload of each microservice and ensure system scalability and reliability. With this approach, it is hoped that the development of a website-based freelance platform can run more efficiently and quickly, so that it can immediately provide optimal services for freelancers in Indonesia.
Optimasi Model Prediksi Kelulusan Mahasiswa Berbasis Principal Component Analysis dan Modified K-Nearest Neighbor Pramnesti, Adisty Regina; Rahajoe, Ani Dijah; Mumpuni, Retno
CICES (Cyberpreneurship Innovative and Creative Exact and Social Science) Vol 11 No 2 (2025): CICES
Publisher : UNIVERSITAS RAHARJA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/cices.v11i2.3914

Abstract

Angka drop-out mahasiswa di perguruan tinggi masih menjadi permasalahan serius karena berdampak pada pemborosan sumber daya dan perkembangan institusi. Identifikasi dini terhadap mahasiswa berisiko drop-out sangat penting, namun metode manual dan algoritma K-Nearest Neighbor (KNN) konvensional masih memiliki keterbatasan, seperti sensitivitas terhadap outlier dan data berdimensi tinggi. Penelitian ini mengusulkan integrasi Principal Component Analysis (PCA) dan Modified K-Nearest Neighbor (MKNN) untuk meningkatkan akurasi klasifikasi kelulusan mahasiswa. PCA digunakan untuk mereduksi 14 variabel menjadi 2 variabel utama, sedangkan MKNN memodifikasi KNN dengan teknik weight voting berbasis jarak serta validasi data latih guna mengurangi perngaruh outlier. Model diujikan dengan skema pembagian data 60:40 (latih:uji) dan parameter optimal k=9. Hasil penelitian menunjukkan bahwa kombinasi PCA dan MKNN mampu mencapai akurasi 99,31%, meningkat 0,93% dibanding KNN standar, serta menghasilkan presisi, recall, dan F1-Score sebesar 99,3%. Temuan ini menegaskan bahwa integrasi reduksi dimensi dan weight voting efektif dalam meningkatkan kinerja klasifikasi, sehingga model ini berpotensi menjadi alat prediksi drop-out yang andal di lingkungan pendidikan tinggi.