Article Per Year (5 Year)
p-Index From 2021 - 2026
1.94
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi dan Ilmu Komputer Communications in Science and Technology Jurnal Penelitian Enjiniring Fakultas Teknik Unhas Asean Journal of Science and Engineering (AJSE) Indonesian Journal of Community and Special Needs Education (IJCSNE) ASEAN Journal for Science and Engineering in Materials ASEAN Journal of Educational Research and Technology
Al Husaeni, Dwi Novia
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Humanities Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Education Engineering Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Materials Science & Nanotechnology Mechanical Engineering Social Sciences Other

Published : 11 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 11 Documents
Search

 1   2 
Identifikasi Pola Risiko Akademik Dan Rekomendasi Peningkatan Kinerja Mahasiswa Menggunakan Metode Association Rules Mining Al Husaeni, Dwi Novia; Nabila, Ghina Firdha; Munir; Wahyudin, Asep; Wibisono, Yudi; Rasim; Riza, Lala Septem
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 13 No 4: Agustus 2026
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.134

Abstract

Penelitian ini dilatarbelakangi oleh kompleksitas faktor non-akademik, seperti gaya hidup dan kondisi sosial ekonomi, yang berpotensi memengaruhi capaian akademik mahasiswa namun belum sepenuhnya dieksplorasi secara sistematis berbasis data. Penelitian ini bertujuan mengidentifikasi pola asosiasi antara gaya hidup, latar belakang keluarga, dan kondisi pembelajaran terhadap status kerja paruh waktu mahasiswa serta dampaknya pada kinerja akademik. Penelitian ini menggunakan pendekatan data mining dengan metode Association Rules Mining (ARM) melalui algoritma Apriori untuk mengekstraksi pola hubungan antarvariabel dari data mahasiswa. Dataset yang digunakan merupakan hasil penggabungan dua dataset akademik dan kebiasaan belajar mahasiswa yang telah melalui proses seleksi variabel, diskretisasi data numerik, serta validasi oleh ahli dan responden. Dengan algoritma Apriori dan validasi holdout, ditemukan 44 aturan asosiasi yang memenuhi kriteria minimum support 0,05 dan confidence 0,8. Kualitas aturan dievaluasi menggunakan metrik support, confidence, dan lift pada data pelatihan dan data pengujian untuk memastikan stabilitas dan konsistensi pola yang dihasilkan. Hasil analisis menunjukkan bahwa mahasiswa yang tidak bekerja paruh waktu umumnya memiliki kualitas tidur yang baik, frekuensi olahraga yang teratur, dukungan ekonomi dari keluarga menengah ke atas, serta akses internet yang memadai, yang merupakan faktor-faktor yang berkorelasi positif dengan performa akademik. Hasil pengujian pada data uji menunjukkan nilai confidence rata-rata di atas 0,8 dan nilai lift lebih besar dari 1, yang mengindikasikan adanya hubungan asosiasi positif antarvariabel. Temuan ini selaras dengan literatur yang menyebut pekerjaan paruh waktu berpotensi mengganggu capaian belajar. Disarankan intervensi berupa beasiswa berbasis kebutuhan, edukasi pola hidup sehat, konseling manajemen waktu, dan peningkatan infrastruktur digital. Penelitian ini berkontribusi pada kebijakan berbasis data untuk mendukung kesejahteraan dan prestasi mahasiswa.   Abstract This study is motivated by the complexity of non-academic factors, such as lifestyle and socioeconomic conditions, which have the potential to influence students’ academic performance but have not yet been systematically explored using data-driven approaches. The study aims to identify association patterns between lifestyle, family background, and learning conditions in relation to students’ part-time employment status and its impact on academic performance. A data mining approach was employed using Association Rules Mining (ARM) with the Apriori algorithm to extract patterns of relationships among variables from student data. The dataset used was obtained from the integration of two academic and learning habit datasets, which underwent variable selection, numerical data discretization, and validation by experts and respondents. Using the Apriori algorithm with holdout validation, 44 association rules were identified that met the minimum criteria of 0.05 support and 0.8 confidence. The quality of the rules was evaluated using support, confidence, and lift metrics on both training and testing datasets to ensure the stability and consistency of the extracted patterns. The results indicate that students who do not engage in part-time work generally exhibit good sleep quality, regular physical activity, sufficient economic support from middle- to high-income families, and adequate internet access—factors that are positively associated with academic performance. Testing results show an average confidence value above 0.8 and lift values greater than 1, indicating positive association relationships among the analyzed variables. These findings are consistent with existing literature suggesting that part-time employment may interfere with academic achievement. Accordingly, interventions such as need-based scholarships, healthy lifestyle education, time management counseling, and improvements in digital infrastructure are recommended. This study contributes to data-driven policymaking to support student well-being and academic success.
Co-Authors Al Husaeni, Dwi Fitria Al Obaidi, Abdulkareem Sh. Mahdi Asep Bayu Dani Nandiyanto Asep Wahyudin Chalim, Saefuddin Chano, Jiraporn Fadhillah, Farid Fiandini, Meli Herniwati, H. Hofifah, Siti Nur Judiasri, Melia Dewi Kusnendar, Jajang Lala Septem Riza M. Munir Mauhibur Rokhman Munir Nabila, Ghina Firdha Nuria Haristiani Prabawa, Harsa Wara Ragadhita, Risti Rasim Rasim, R. Roestamy, Martin Santoso, Yoga Budhi Wibisono, Yudi