PREDIKSI TINGKAT KELULUSAN SISWA MENGGUNAKAN ALGORITMA NAIVE BAYES BERDASARKAN DATA AKADEMIK DAN NON AKADEMIK (STUDI KASUS : SMA NEGERI 1 RANTAU UTARA)

JUNIATI SURISTIANI DALIMUNTHE, NPM 2109100040 (2025) PREDIKSI TINGKAT KELULUSAN SISWA MENGGUNAKAN ALGORITMA NAIVE BAYES BERDASARKAN DATA AKADEMIK DAN NON AKADEMIK (STUDI KASUS : SMA NEGERI 1 RANTAU UTARA). Skripsi thesis, Universitas Labuhanbatu.

	Text COVER.pdf Download (1MB)
	Text BAB I.pdf Download (271kB)
	Text BAB II.pdf Download (504kB)
	Text BAB III.pdf Download (823kB)
	Text BAB IV.pdf Download (3MB)
	Text BAB V.pdf Download (218kB)
	Text DAFTAR PUSTAKA.pdf Download (188kB)

Abstract

Skripsi ini bertujuan untuk mengembangkan model prediksi tingkat kelulusan siswa di SMA Negeri 1 Rantau Utara dengan menggunakan algoritma Naive Bayes. Penelitian ini dilatarbelakangi oleh pentingnya prediksi kelulusan sebagai indikator keberhasilan pendidikan yang dapat membantu institusi dalam mengevaluasi dan meningkatkan kualitas program pendidikan. Data yang digunakan mencakup variabel akademik seperti nilai ujian, nilai tugas harian, dan absensi, serta variabel non-akademik seperti latar belakang ekonomi, partisipasi dalam kegiatan ekstrakurikuler, dan motivasi belajar. Metodologi penelitian meliputi pengumpulan data dari siswa kelas X, pembersihan data untuk menghilangkan entri yang tidak relevan, serta pemrosesan untuk membangun model prediksi. Setelah dilakukan evaluasi, model Naive Bayes menunjukkan hasil yang memuaskan dengan akurasi sebesar 95%, presisi 92%, dan recall 100%. Hasil penelitian ini diharapkan dapat memberikan wawasan bagi pihak sekolah dalam melakukan intervensi dini terhadap siswa yang berisiko tidak lulus, serta berkontribusi pada peningkatan kualitas pendidikan secara keseluruhan. Kata Kunci: Prediksi, Tingkat Kelulusan, Naive Bayes, Data Akademik, Data Non-Akademik, Model Prediksi ================================================================================================= This thesis aims to develop a prediction model for student graduation rates at SMA Negeri 1 Rantau Utara using the Naive Bayes algorithm. This research is motivated by the importance of graduation prediction as an indicator of educational success that can assist institutions in evaluating and improving the quality of educational programs. The data used includes academic variables such as exam scores, daily assignments, and attendance, as well as non-academic variables such as economic background, participation in extracurricular activities, and learning motivation. The research methodology included data collection from 10th-grade students, data cleaning to remove irrelevant entries, and data processing to build a prediction model. After evaluation, the Naive Bayes model demonstrated satisfactory results with 95% accuracy, 92% precision, and 100% recall. The results of this study are expected to provide insight for schools in implementing early intervention for students at risk of failing and contribute to improving the overall quality of education. Keywords: Prediction, Graduation Rate, Naive Bayes, Academic Data, Non Academic Data, Prediction Model

Item Type:	Thesis (Skripsi)
Uncontrolled Keywords:	Prediksi, Tingkat Kelulusan, Naive Bayes, Data Akademik, Data Non-Akademik, Model Prediksi=================Prediction, Graduation Rate, Naive Bayes, Academic Data, Non Academic Data, Prediction Model
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science T Technology > T Technology (General) Z Bibliography. Library Science. Information Resources > Z665 Library Science. Information Science Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4050 Electronic information resources Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4450 Databases
Divisions:	Fakultas Sains Dan Teknologi > Sistem Informasi
Depositing User:	Unnamed user with email repository@ulb.ac.id
Date Deposited:	14 Oct 2025 04:18
Last Modified:	14 Oct 2025 04:18
URI:	http://repository.ulb.ac.id/id/eprint/1799

Actions (login required)

View Item