PENERAPAN TEKNIK DATA MINING UNTUK MENENTUKAN POLA KINERJA SISWA SD SANTA MARIA REMBANG DALAM MENGHADAPI UJIAN KELULUSAN

Sholihul Ibad

Abstract


APPLICATION OF DATA MINING TECHNIQUES TO DETERMINE PERFORMANCE PATTERNS OF STUDENTS AT SD SANTA MARIA REMBANG IN FACING THE GRADUATION EXAM

SD Santa Maria is one of the elementary school in Rembang Regency. SD Santa Maria has problems with the performance or reduced ability of students in the matriculation examination, especially failures in mathematics and language tests. The purpose of this study is to group students on the basis of student performance and on the basis of the formed groups to determine the pattern of student performance when approaching the matriculation exam. The proposed method focuses on clustering and classification methods. The K-Means clustering method aims to find the best number of groups (clusters) and groups of students in the respective clusters. Therefore, the proposed classification method uses a decision tree algorithm to find patterns of students based on the created groups (clusters). The results of this research showed that k = 2 as the best group (cluster) and the grouping of students into 2 groups (cluster 0 and cluster 1). The clustering results with clusters as a new attribute are used for the classification method of the decision tree algorithm. Clusters are used as labels and the resulting patterns are in the form of decision trees or rules.

 

SD Santa Maria merupakan salah satu Sekolah Dasar yang berada di Kabupaten Rembang. Saat menghadapi  ujian kelulusan, SD Santa Maria memiliki masalah kinerja atau kemampuan siswanya menurun, khuhusnya kegagalan pada ujian matematika dan bahasa. Tujuan dari penelitian ini adalah mengelompokkan siswa berdasarkan kinerja siswa dan mengetahui pola dari kinerja siswanya dalam menghadapi ujian kelulusan berdasarkan kelompok yang terbentuk.  Metode yang diusulkan terfokus pada metode clustering dan klasifikasi. Metode clustering dengan menggunakan algoritma K-Means bertujuan untuk mencari jumlah kelompok (cluster) yang paling optimal dan mengelompokkan siswa pada cluster yang sesuai. Dengan demikian, metode klasifikasi yang diusulkan menggunakan algoritma Decision Tree untuk menemukan pola dari siswa berdasarkan kelompok (cluster) yang terbentuk. Hasil penelitian ini menghasilkan k=2 sebagai kelompok (cluster) yang paling optimal dan mengelompokkan siswa menjadi 2 kelompok (cluster 0 dan cluster 1). Hasil cluster yang memuat cluster sebagai atribut baru ini lah yang digunakan untuk metode klasifikasi dengan algoritma Decision Tree. Cluster dijadikan sebagai label dan pola yang dihasilkan berbentuk decision tree (pohon keputusan)  atau peraturan if-then.


Keywords


Student Performance; Data Mining; Clustering; Classification; Kinerja Siswa; Data Mining; Clustering; Klasifikasi;

Full Text:

PDF

References


C. Romero and S. Ventura, “Educational data mining: A review of the state of the art,” IEEE Trans. Syst. Man Cybern. Part C Appl. Rev., vol. 40, no. 6, pp. 601–618, 2019, doi: 10.1109/TSMCC.2010.2053532.

M. Sadikin, R. Rosnelly, and T. Surya Gunawan, “Perbandingan Tingkat Akurasi Klasifikasi Penerimaan Dosen Tetap Menggunakan Metode Naive Bayes Classifier dan C4.5,” J. Media Inform. Budidarma, vol. 4, no. 4, pp. 1100–1109, 2020, doi: 10.30865/mib.v4i4.2434.

F. Harahap, “Perbandingan Algoritma K Means dan K Medoids Untuk Clustering Kelas Siswa Tunagrahita,” TIN Terap. Inform. Nusant., vol. 2, no. 4, pp. 191–197, 2021.

A. Abu, “Educational Data Mining & Students’ Performance Prediction,” Int. J. Adv. Comput. Sci. Appl., vol. 7, no. 5, pp. 212–220, 2019, doi: 10.14569/ijacsa.2016.070531.

P. Cortez and A. Silva, “Using data mining to predict secondary school student performance,” 15th Eur. Concurr. Eng. Conf. 2008, ECEC 2008 - 5th Futur. Bus. Technol. Conf. FUBUTEC 2008, vol. 2003, no. 2000, pp. 5–12, 2018.

F. Widyahastuti and V. U. Tjhin, “Student Performance Prediction Using Data Mining Techniques,” no. May, pp. 90–95, 2020, doi: 10.5220/0009017000900095.

B. Kumar and S. Pal, “Mining Educational Data to Analyze Students Performance,” Int. J. Adv. Comput. Sci. Appl., vol. 2, no. 6, 2019, doi: 10.14569/ijacsa.2011.020609.

N. Z. Rahma and A. Setyono, “Implementation of C4 . 5 Algorithm to Predict the Ability of Junior High School Student to Face National Exam,” vol. 8, no. 1, pp. 35–46, 2019.

F. N. R. F. J. Aziz, B. D. Setiawan, and I. Arwani, “Implementasi Algoritma K-Means untuk Klasterisasi Kinerja Akademik Mahasiswa,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 2, no. 6, pp. 2243–2251, 2019.

M. North, Data Mining for the Masses. 2012.




DOI: https://doi.org/10.34001/jdpt.v15i1.4920

Article Metrics

Abstract view : 98 times
PDF - 42 times

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Disprotek Indexed by:

1 Google Scholar 2 BASe3 Onsesearch 4 Garuda 5 Sinta 6 Dimensions7 Crossref 8 JurnalStories 9 ROAD 10 ICE11 ORCID  

Visitor Statistics
Web Analytics Made Easy - StatCounter
Flag Counter

Lisensi Creative Commons

DISPROTEK: Journal of Informatics Engineering, Information Systems, Electrical Engineering, Industrial Engineering, Civil Engineering, and Aquaculture is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.