Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal IKRA-ITH Informatika : Jurnal Komputer dan Informatika Jurnal Komputer dan Sistem Informasi
Yahya Yahya
Program Studi Teknologi Informasi Universitas Darma Persada
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Evaluasi Kinerja Datamining Pada Dataset Pendaftaran Mahasiswa Baru Dengan Class Yang Tidak Seimbang Herianto Herianto; Nur Syamsiyah; Adam Arif B; Yahya Yahya
ikraith-informatika Vol 5 No 3 (2021): IKRAITH-INFORMATIKA Vol 5 No 3 November 2021
Publisher : Fakultas Teknik Universitas Persada Indonesia YAI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (999.685 KB)

Abstract

Topik penelitian ini di bidang EDM (Educational Datamining) yang bertujuanmemanfaatkan datamining dalam memperoleh informasi yang lebih bernilai daridatabase akademik Perguruan Tinggi. Penggunaan data pendaftaran mahasiswabaru karena karakteristik datanya yang umumnya tidak seimbang (imbalancedclass) sehingga dapat digunakan untuk menguji dan membandingkan kinerja modelpembelajaran machine learning. Perkakas yang digunakan adalah Jupyter sebagaieditor, Python sebagai bahasa pemrogramannya dan Library sklearn sebagai modulterpopular di bidang machine learning. Metodologi penelitian mengacu kepadaCRISP-DM sebagai metodologi yang bersifat terbuka. Percobaan dilakukanmenggunakan 7491 data, 5 kolom sebagai fitur dan 1 kolom sebagai target. Kelasbernilai 1 sebanyak 6197 (82,5%) dan yang bernilai 0 sebanyak 1312 (17,5%).Kemudian dibangun model klasifikasi dengan pembelajaran berbeda yaitu : SVM(Support Vector Machine), Logistic Regression, Decision Tree, Naive Bayes, danK-Nearest Neighbors (K-NN). Dari hasil percobaan diperoleh rata-rata akurasisemua model sebesar 0,81 dan nilai rata-rata F Score 0,46. Nilai Akurasi tertinggi0,82, dan akurasi terendah 0,81. Nilai F Score tertinggi 0,51 dan nilai F Scoreterendah adalah 0,44. Hasil ini kembali mengungkap bahwa pada kasus dengankomposi data target yang tidak seimbang (Imbalanced Classes) memungkinkanuntuk menghasilkan akurasi yang baik tetapi tidak menjamin nilai F Score baik.
RANCANG BANGUN SISTEM INFORMASI PENILAIAN KINERJA TUTOR MENGGUNAKAN METODE AHP PADA CV. INTERLEARNING CENTRE Eva Novianti; Yahya; Yahya Ananda
Jurnal Komputer dan Sistem Informasi Vol. 3 No. 2 (2026): Juni 2026
Publisher : Indie Press Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66865/qqehyv04

Abstract

The growth of digital economic transactions in Indonesia encourages tight competition among digital wallet service providers, including the DANA application. User satisfaction is the key to maintaining relevance in the 2025 fintech market. This study aims to evaluate the influence of Content, Accuracy, Format, Ease of Use, and Timeliness variables on DANA User Satisfaction through the End-User Computing Satisfaction (EUCS) framework. The methodology used is quantitative with a sample of 111 respondents and multiple linear regression analysis. The test results show that the model has a coefficient of determination (R pangkat 2) of 51.6%. Partially, the Format variable has the most dominant positive influence. CV. Interlearning Centre is a tutoring institution that requires an objective, well-documented, and easy-to-use tutor performance assessment system for personnel staff, managers, tutors, and students. This study aims to design and develop a web-based tutor performance assessment information system using the Analytic Hierarchy Process (AHP) as the sole priority calculation method. The system development method applies the waterfall model, consisting of requirements analysis, system design, implementation, testing, and maintenance. The required data were obtained through observation of the existing process, interviews with personnel staff, and literature study. The AHP method is used to construct the decision hierarchy, develop pairwise comparison matrices, calculate criteria weights, test consistency, and generate the final tutor performance scores. The design results show that the system can manage tutor data, criteria, subcriteria, assessment periods, AHP comparisons, score inputs, and tutor ranking reports. Functional testing indicates that all main features operate according to the specified requirements. This study contributes to providing a simpler, more transparent, and measurable tutor performance assessment system model using AHP.
Co-Authors Adam Arif B Eva Novianti Herianto Nur Syamsiyah Yahya Ananda