Claim Missing Document
Check
Articles

Found 23 Documents
Search

Perbandingan Algoritma Klasifikasi Decision Tree, Random Forest, dan Naive Bayes dalam Prediksi Kelulusan Mahasiswa Sartika Lina Mulani Sitio; Susanna Dwi Yulianti Kusuma; Hidayatullah Al Islami; Mukti Andrianto
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 7 No. 3 (2026): September
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63447/jimik.v7i3.2082

Abstract

Timely graduation is one of the important indicators of academic success of universities. However, the student monitoring process still faces obstacles in identifying students who have the potential to not graduate on time. This study offers a solution in the form of applying machine learning to predict graduation status while comparing the most effective algorithms. The research uses 750 data of students of the Informatics Study Program batch 2017 – 2021 sourced from the Academic Information System. The research methods include data preprocessing, handling missing values and outliers, encoding, normalization, forming Decision Tree, Random Forest, and Naïve Bayes models, as well as evaluation using accuracy, precision, recall, F1-score, and AUC-ROC. The results of the study show that Random Forest provides the best performance with an accuracy of 91.33%, precision of 90.48%, recall of 93.42%, F1-score of 91.93%, and an AUC-ROC of 0.952. Decision Tree obtained an accuracy of 84.67%, while Naïve Bayes was 80.00%. The Friedman test resulted in a value of p = 0.015 which showed a significant difference in performance. Thus, Random Forest is the best algorithm for predicting student graduation in this research dataset and has the potential to support academic early warning systems.
Implementation of a Decision Support System for Selection of Mechanical and Electrical Materials Using a Web-Based Smart Method Jul Padri; Susanna Dwi Yulianti Kusuma
Jurnal Teknologi Informatika dan Komputer Vol. 12 No. 2 (2026): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v12i2.3923

Abstract

This research was motivated by the material selection process for mechanical and electrical materials at PT. Tirta Gitacana Sakti, which was not yet supported by an integrated web-based system for managing material data and storing assessment history. This condition caused the decision-making process to require a relatively long time and potentially resulted in inconsistencies in the assessment process. In addition, the material assessment process had not yet used a structured decision-making method, causing the results to remain subjective and less measurable. This research aims to design and develop a web-based Decision Support System (DSS) that can manage material data, store assessment history, and improve efficiency and consistency in the selection of mechanical and electrical materials. This research also aims to implement the SMART (Simple Multi-Attribute Rating Technique) method to produce a more objective, structured, and measurable assessment process and provide recommendations for the best materials. The system was developed using the Waterfall method, while system testing was conducted using Black Box Testing and White Box Testing with the Basis Path Testing technique. The SMART method was implemented through criteria weight normalization, utility value calculation based on Benefit and Cost criteria, and final value calculation to generate material rankings. The results show that the developed system successfully integrates the management of material, supplier, criteria, assessment, assessment period, assessment history, approval, reporting, and audit log data. The implementation of the SMART method successfully produces final values and material rankings as a basis for providing recommendations.
IMPLEMENTASI SISTEM PENDUKUNG KEPUTUSAN DALAM MENENTUKAN WAKTU TANAM KOPI TERBAIK DENGAN METODE SMARTER BERBASIS WEB(STUDI KASUS: DESA TALANG BENTENG) Tira; Susanna Dwi Yulianti Kusuma
PROSISKO: Jurnal Pengembangan Riset dan Observasi Sistem Komputer Vol. 13 No. 3 (2026): Prosisko Vol. 13 No. 3 November 2026
Publisher : Pogram Studi Sistem Komputer Universitas Serang Raya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30656/prosisko.v13i3.12003

Abstract

Penentuan waktu tanam kopi merupakan salah satu faktor penting yang mempengaruhi keberhasilan produksi kopi. Pada perkebunan kopi Talang Benteng, proses penentuan waktu tanam masih dilakukan secara manual berdasarkan pengalaman petani sehingga berpotensi menghasilkan keputusan yang kurang. Oleh karena itu diperlukan suatu sistem yang dapat membantu dalam menentukan waktu tanam kopi yang optimal.  Penelitian ini bertujuan untuk merancang dan membangun sistem pendukung keputusan berbasis web untuk menentukan waktu tanam kopi terbaik menggunakan metode SMARTER (Simple Multi Attribute Rating Technique Exploiting ranks). Metode SMARTER digunakan untuk melakukan pembobotan kriteria dengan pendekatan Rank Order Centroid (ROC) serta melakukan proses perangkingan alternatif bulan tanam. Kriteria yang digunakan dalam penelitian ini meliputi curah hujan, suhu udara, kelembapan udara, sinar matahari, dan kecepatan angin. Alternatif yang digunaan adalah dua belas bulan dalam satu tahun. Hasil penelitian ini menunjukkan bahwa bulan desember memperoleh nilai preferensi tertinggi terbesar 0,4689 sehingga direkomendasikan sebagai waktu tanam kopi terbaik dibandingkan bulan lainnya. Sistem yang dibangun mampu membantu proses pengambilan keputusan secara lebih objektif dan sistmatis dalam menentukan waktu tanam kopi yang optimal.