PENERAPAN ALGORITMA K-MEANS CLUSTERING DALAM PENGELOMPOKAN HASIL BELAJAR SISWA DI SMP BUDI LUHUR SAMARINDA

Fatimah, Khoirulli Nurul (2024) PENERAPAN ALGORITMA K-MEANS CLUSTERING DALAM PENGELOMPOKAN HASIL BELAJAR SISWA DI SMP BUDI LUHUR SAMARINDA. S1 Teknik Informatika thesis, STMIK Widya Cipta Dharma.

[img] Text
2043004-S1-Teknik Informatika.pdf
Restricted to Repository staff only
Download (3MB) | Request a copy
[img] Text
2043004-S1-Jurnal.pdf
Download (674kB)

Abstract

ABSTRAK Khoirulli Nurul Fatimah, 2024, Penerapan Algoritma K-Means Clustering dalam Pengelompokan Hasil Belajar Siswa di SMP Budi Luhur Samarinda. Skripsi Program Studi Teknik Informatika, Sekolah Tinggi Manajamen Informatika dan Komputer Widya Cipta Dharma, Pembimbing (I) Dr. Heny Pratiwi, S.Kom., M.Pd., M.TI., Pembimbing (II) Eka Arriyanti, S.Pd., M.Kom. Kata Kunci: Clustering, K-Means, Hasil Belajar Siswa Penelitian ini bertujuan untuk mengelompokkan hasil belajar siswa di SMP Budi Luhur Samarinda guna membantu siswa dalam memilih jurusan yang sesuai di jenjang SMA berdasarkan potensi dan kemampuan akademik mereka. Dengan menerapkan algoritma K-Means Clustering dalam metode Knowledge Discovery in Databases (KDD), diharapkan siswa dapat memperoleh panduan yang lebih tepat untuk menentukan jurusan dan mengoptimalkan prestasi akademik mereka. Metode penelitian ini melibatkan tahap-tahap Knowledge Discovery in Databases (KDD), yaitu pembersihan data, integrasi data, seleksi data, transformasi data, penambangan data (data mining), interpretasi, dan evaluasi. Data yang digunakan terdiri dari nilai akademik 76 siswa SMP Budi Luhur Samarinda, mencakup nilai rara-rata keseluruhan mata pelajaran, rata-rata mata pelajaran eksak dan non-eksak, yang diolah menggunakan Python untuk analisis dan Streamlit untuk visualisasi serta interaksi pengguna. Hasil analisis menunjukkan bahwa jumlah cluster optimal adalah dua, dengan nilai silhouette score sebesar 0,56. Cluster pertama terdiri dari 35 siswa (46%) dengan nilai rata-rata eksak dan non-eksak yang lebih rendah, sedangkan cluster kedua terdiri dari 41 siswa (54%) dengan nilai rata-rata yang lebih tinggi. Temuan ini diharapkan dapat memberikan wawasan yang lebih jelas mengenai potensi akademik siswa dan mendukung keputusan mereka dalam memilih jurusan di SMA. ========================================================================================================= ABSTRACT Khoirulli Nurul Fatimah, 2024, Application of K-Means Clustering Algorithm in Grouping Student Learning Outcomes at SMP Budi Luhur Samarinda. Thesis, Department of Informatics Engineering, Widya Cipta Dharma School of Information Management and Computer Science, Advisor (I) Dr. Heny Pratiwi, S.Kom., M.Pd., M.TI., Advisor (II) Eka Arriyanti, S.Pd., M.Kom. Keywords: Clustering, K-Means, Student Learning Outcomes This study aims to group the learning outcomes of students at SMP Budi Luhur Samarinda to assist them in choosing appropriate majors at the senior high school level based on their potential and academic abilities. By applying the K-Means Clustering algorithm within the Knowledge Discovery in Databases (KDD) method, it is hoped that students will receive more accurate guidance for selecting their majors and optimizing their academic performance. The research methodology involves several stages of the KDD process, including data cleaning, data integration, data selection, data transformation, data mining, interpretation, and evaluation. The data used consists of academic scores from 76 students at SMP Budi Luhur Samarinda, including overall average scores, as well as averages for exact and non-exact subjects, processed using Python for analysis and Streamlit for visualization and user interaction. The analysis results indicate that the optimal number of clusters is two, with a silhouette score of 0.56. The first cluster comprises 35 students (46%) with lower average scores in both exact and non-exact subjects, while the second cluster includes 41 students (54%) with higher average scores. These findings are expected to provide clearer insights into students' academic potential and support their decision-making process for choosing majors in senior high school.

Item Type: Thesis (S1 Teknik Informatika)
Additional Information: Pembimbing 1 = Dr. Heny Pratiwi, S.Kom., M.Pd., M.TI. Pembimbing 2 = Eka Arriyanti, S.Pd., M.Kom.
Uncontrolled Keywords: Clustering, K-Means, Hasil Belajar Siswa
Subjects: Q Science > QA Mathematics > QA76 Computer software
Divisions: Teknik Informatika
Depositing User: Ms Khoirulli Nurul Fatimah
Date Deposited: 08 Aug 2024 06:28
Last Modified: 08 Aug 2024 06:28
URI: http://repository.wicida.ac.id/id/eprint/5791

Actions (login required)

View Item View Item
wicida repository is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.