Joint Workshop KO2PI and The 1st International Conference on Advance & Scientific Innovation

Research Article

Analysis of Student Demographic Information Using Data Mining classification with Decision Tree

Download712 downloads
  • @INPROCEEDINGS{10.4108/eai.23-4-2018.2277561,
        author={Citra Kurniawan and Ifit Novita Sari and Diah Puji Nali Brata},
        title={Analysis of Student Demographic Information Using Data Mining classification with Decision Tree},
        proceedings={Joint Workshop KO2PI and The 1st International Conference on Advance \& Scientific Innovation},
        publisher={EAI},
        proceedings_a={ICASI},
        year={2018},
        month={7},
        keywords={data mining decision tree student demographic},
        doi={10.4108/eai.23-4-2018.2277561}
    }
    
  • Citra Kurniawan
    Ifit Novita Sari
    Diah Puji Nali Brata
    Year: 2018
    Analysis of Student Demographic Information Using Data Mining classification with Decision Tree
    ICASI
    EAI
    DOI: 10.4108/eai.23-4-2018.2277561
Citra Kurniawan1,*, Ifit Novita Sari2, Diah Puji Nali Brata3
  • 1: Sekolah Tinggi Teknik Malang, Jl. Soekarno Hatta Nomor 94 Malang, East Java, Indonesia
  • 2: University of Kanjuruhan Malang, Jl. S. Supriadi 48 Malang, East Java, Indonesia
  • 3: STKIP PGRI Jombang, Jl. Pattimura III No. 20 Jombang, East Java, Indonesia
*Contact email: airakurniawan@gmail.com

Abstract

The purpose of this study was to process Student Demographic Information using data mining analysis using decision tree technique. This study retrieved data from 50 students with visual data attributes - verbal preferences, self-efficacy, gender, and interest. This study uses orange data mining to process data with decision tree technique. The study found that decision node as the best predictors are visual preferences, in which visuals had a 76% of 50 attributes. Female students had a 100% distribution as a visual preference, while male had 68.4% of the distribution as a visual preference. The results found that the attributes that predictor were visual preferences. The decision tree gets the rule from the root node to the leaf nodes as many as four rules are R1, R2, R3, and R4.