<![CDATA[Penelitian ini bertujuan untuk mengklasifikasikan prestasi akademik siswa dengan mempertimbangkan berbagai faktor yang memengaruhi hasil belajar. Algoritma Decision Tree diimplementasikan menggunakan perangkat lunak RapidMiner dengan data bersumber dari dataset Student Performance Factors. Dataset tersebut memuat atribut seperti Hours_Studied, Attendance, Parental_Involvement, Access_to_Resources, Previous_Scores, Motivation_Level, Sleep_Hours, Internet_Access, dan Tutoring_Sessions, dengan Exam_Score sebagai label target. Proses penelitian meliputi tahapan pengumpulan, pembersihan, dan transformasi data, kemudian pembagian data menjadi 80% data latih dan 20% data uji. Hasil analisis menunjukkan bahwa atribut Hours_Studied dan Attendance merupakan faktor dominan dalam menentukan prestasi siswa. Model pohon keputusan berhasil mengelompokkan siswa ke dalam tiga kategori, yaitu Low (100 data), Medium (4.498 data), dan High (27 data) dari total 4.625 data. Temuan ini membuktikan bahwa metode Decision Tree efektif untuk mengenali pola hubungan faktor belajar terhadap prestasi akademik dan dapat menjadi dasar evaluasi bagi pihak sekolah dalam meningkatkan kualitas pembelajaran. Kata Kunci: Decision Tree, RapidMiner, Data Mining, Klasifikasi Prestasi Akademik, Student Performance Factors This study aims to classify students' academic achievement by considering various factors that influence learning outcomes. The Decision Tree algorithm was implemented using RapidMiner software with data sourced from the Student Performance Factors dataset. The dataset contains attributes such as Hours_Studied, Attendance, Parental_Involvement, Access_to_Resources, Previous_Scores, Motivation_Level, Sleep_Hours, Internet_Access, and Tutoring_Sessions, with Exam_Score as the target label. The research process included data collection, cleaning, and transformation, followed by dividing the data into 80% training data and 20% test data. The analysis results showed that the attributes Hours_Studied and Attendance were dominant factors in determining student achievement. The decision tree model successfully grouped students into three categories, namely Low (100 data), Medium (4,498 data), and High (27 data) from a total of 4,625 data. These findings prove that the Decision Tree method is effective in recognizing patterns of the relationship between learning factors and academic achievement and can be used as a basis for evaluation by schools in improving the quality of learning. Keyword :Decision Tree, RapidMiner, Data Mining, Academic Achievement Classification, Student Performance Factors]]>
Copyrights © 2026
