ANALISIS PREDIKSI PRESTASI BELAJAR SISWA SD NEGERI 117854 SIKOPI-KOPI DESA PULO DOGOM MENGGUNAKAN ALGORITMA DECISION TREE (C4.5) PADA RAPIDMINER

FEBY WIDIA NINGSIH, NPM 2209500181 (2026) ANALISIS PREDIKSI PRESTASI BELAJAR SISWA SD NEGERI 117854 SIKOPI-KOPI DESA PULO DOGOM MENGGUNAKAN ALGORITMA DECISION TREE (C4.5) PADA RAPIDMINER. Skripsi thesis, Universitas Labuhanbatu.

	Text COVER.pdf Download (959kB)
	Text BAB I.pdf Download (323kB)
	Text BAB II.pdf Download (578kB)
	Text BAB III.pdf Restricted to Registered users only Download (723kB)
	Text BAB IV.pdf Restricted to Registered users only Download (1MB)
	Text BAB V.pdf Download (307kB)
	Text DAFTAR PUSTAKA.pdf Download (320kB)
	Text LAMPIRAN.pdf Download (843kB)

Abstract

Kemajuan educational data mining (EDM) membuka peluang bagi lembaga pendidikan untuk memprediksi prestasi belajar siswa secara lebih akurat. Namun, SD Negeri 117854 Sikopi-Kopi Desa Pulo Dogom masih mengelola data nilai siswa secara manual sehingga deteksi dini siswa berisiko sulit dilakukan. Penelitian ini bertujuan untuk mengetahui penerapan algoritma Decision Tree C4.5 dalam memprediksi prestasi belajar siswa, mengetahui tingkat akurasi model yang dihasilkan, serta mengidentifikasi atribut yang paling berpengaruh terhadap hasil prediksi. Penelitian menggunakan pendekatan kuantitatif dengan data nilai akademik 43 siswa pada enam mata pelajaran (Pendidikan Agama, Pendidikan Pancasila, Bahasa Indonesia, Matematika, Seni Rupa, dan PJOK), yang diolah melalui tahapan KDD meliputi seleksi, pembersihan, transformasi, dan pembagian data (80:20) sebelum diklasifikasikan menggunakan algoritma C4.5 pada aplikasi RapidMiner dengan validasi Cross Validation. Hasil penelitian menunjukkan model mencapai akurasi sebesar 97,67%, dengan atribut Pendidikan Agama (X1) terpilih sebagai root node berdasarkan nilai gain ratio tertinggi (0,7783), setara dengan atribut PJOK (X6). Dapat disimpulkan bahwa algoritma C4.5 mampu menghasilkan model prediksi prestasi belajar siswa sekolah dasar dengan tingkat akurasi tinggi dan dapat dijadikan alat bantu deteksi dini oleh pihak sekolah. Kata kunci: Decision Tree C4.5, Prediksi Prestasi Belajar, Rapidminer, Educational Data Mining, Gain Rasio ===================================================================================== Advances in educational data mining (EDM) have opened opportunities for educational institutions to predict student learning achievement more accurately. However, SD Negeri 117854 Sikopi-Kopi in Pulo Dogom Village still manages student grade data manually, making early detection of at-risk students difficult. This study aims to examine the implementation of the Decision Tree C4.5 algorithm in predicting student learning achievement, determine the accuracy level of the resulting model, and identify the attribute with the greatest influence on prediction results. This study employed a quantitative approach using academic score data from 43 students across six subjects (Religious Education, Pancasila Education, Indonesian Language, Mathematics, Fine Arts, and Physical Education), processed through KDD stages including selection, cleaning, transformation, and an 80:20 data split, before being classified using the C4.5 algorithm in RapidMiner with Cross Validation. The results show that the model achieved an accuracy of 97.67%, with the Religious Education attribute (X1) selected as the root node based on the highest gain ratio value (0.7783), tied with the Physical Education attribute (X6). It can be concluded that the C4.5 algorithm is able to produce a highly accurate prediction model for elementary school student achievement and can serve as an early detection tool for schools. Keywords: Decision Tree C4.5, Learning Achievement Prediction, Rapidminer, Educational Data Mining, Gain Ratio

Item Type:	Thesis (Skripsi)
Uncontrolled Keywords:	Decision Tree C4.5, Prediksi Prestasi Belajar, Rapidminer, Educational Data Mining, Gain Rasio=================Decision Tree C4.5, Learning Achievement Prediction, Rapidminer, Educational Data Mining, Gain Ratio
Subjects:	Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General) 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:	27 Aug 2026 03:21
Last Modified:	27 Aug 2026 03:21
URI:	http://repository.ulb.ac.id/id/eprint/2680

Actions (login required)

View Item