ANALISIS POTENSIAL DROP OUT MAHASISWA DENGAN K-MEANS++ CLUSTERING DALAM UPAYA PENINGKATAN KUALITAS IAIN KEDIRI

Authors

  • Ummiy Fauziyah Laili Institut Agama Islam Negeri (IAIN) Kediri, Indonesia
  • Choiru Umatin Institut Agama Islam Negeri (IAIN) Kediri, Indonesia
  • M. Ubaidillah Ridwanulloh Institut Agama Islam Negeri (IAIN) Kediri, Indonesia

DOI:

https://doi.org/10.31764/paedagoria.v14i2.14077

Keywords:

Potensial Drop Out, K-Means Clustering, Kualitas

Abstract

Abstrak: Penelitian ini  bertujuan untuk menganalisi potensi dropout mahasiswa  dengan menggunakan metode analisis clustering data mining dengan algoritma Kmeans++, dengan pengukuran tingkat keakuratan clustering menggunakan silhouette coefficient dan purity. Penelitian ini didekati dengan metode penelitian kuantitatif dengan metode analisis data Teknik clustering dengan Langkah-langkah pada algoritma K-Means++. Data yang digunakan dalam penelitian ini adalah data akademis mahasiswa IAIN Kediri tahun akademik 2016/2017 – 2019/2020, atribut yang digunakan sebagai data adalah yaitu nilai Index Prestasi komulatif Mahasiswa (IPK), total satuan kredit semester (SKS), dan Semester yang sudah ditempuh mahasiswa. Hasil penelitian menunjukkan hasil 3 percobaan yakni membentuk 3,4 dan 5 cluster diperoleh hasil bahwa Fakultas yang memiliki potensi Drop Out tertinggi adalah Fakultas Tarbiyah, kedua Fakultas Ushuludin dan Filsafat, ketiga Fakultas Ekonomi dan Bisnis Islam, dan terakhir Fakultas Syari’ah. Permasalahan Drop Out di IAIN Kediri terus dijadikan evaluasi karena memberikan dampak yang besar bagi pihak mahasiswa, keluarga dan juga institusi. Hal ini disebabkan minat belajar yang rendah, kurang adaptasi secara akademik dan social dan mhasiswa merasakan kesulitas memahami bidang ilmu baru disemester awal.

Abstract: The purpose of this study is to classify and explain students who have the potential to drop out using the K-Means ++ algorithm and find out the evaluation of grouping students who have the potential to drop out using the silhouette coefficient and purity methods. The research method used is a quantitative approach. The technique used is the clustering technique with steps on the K-Means++ algorithm. Samples of data taken from the 2016/2017 – 2019/2020 class, namely the value of Student Achievement Index (GPA), total semester credit units (SKS), and Semester took. The results showed that the results of 3 trials, namely forming 3,4 and 5 clusters, showed that the faculties with the highest dropout potential were the Tarbiyah Faculty, the two Ushuludin and Philosophy Faculties, the three Islamic Economics and Business Faculties, and lastly the Syari'ah Faculty. The Drop Out problem at IAIN Kediri continues to be used as an evaluation because it has a big impact on students, families, and also institutions. This is due to low interest in learning, lack of adaptation academically and socially and students finding it difficult to understand new fields of knowledge in the early semester.

References

Anwar, M. T., Heriyanto, L., & Fanini, F. (2021). Model Prediksi Dropout Mahasiswa Menggunakan Teknik Data Mining. Jurnal Informatika Upgris, 7(1). https://doi.org/10.26877/jiu.v7i1.8023

Bahri, S., & Midyanti, D. M. (2023). Penerapan Metode K-Medoids untuk Pengelompokan Mahasiswa Berpotensi Drop Out. Jurnal Teknologi Informasi dan Ilmu Komputer, 10(1), Article 1. https://doi.org/10.25126/jtiik.20231016643

FALAHI, F. M. (n.d.). Penerapan Metode Clustering Untuk Pengelompokan Mahasiswa Potensial Drop Out Menggunakan.

Firmansyah, A., Gufroni, A. I., & Rachman, A. N. (2017). Data Mining dengan Metode Clustering K-mean untuk Pengelompokan Mahasiswa Potensial Drop Out pada Program Studi Teknik Informatika Universitas Siliwangi. Teknik Informatika Universitas Siliwangi Tasikmalaya.

Fitro, A., Rudianto, R., & Prasetyo, H. (2021). Implementasi Metode Grey Verhulst untuk Mendukung Kebijakan dalam Mengantisipasi Mahasiswa Dropout. Jurnal Ilmiah Intech : Information Technology Journal of UMUS, 3(02), 180–187. https://doi.org/10.46772/intech.v3i02.585

Ilmiah, I., & Utomo, T. (2020). Hubungan Self Confidence dengan Adversity Quotient pada Mahasiswa Pasca Drop Out di Universitas Trunojoyo Madura. Personifikasi: Jurnal Ilmu Psikologi, 11(1), Article 1. https://doi.org/10.21107/personifikasi.v11i1.7289

Kristyawan, Y., & Sumirat, L. P. (2019). Analisis Terhadap Faktor-Faktor Yang Mempengaruhi Mahasiswa Gagal Studi Menggunakan Teknik Klasifikasi. Jurnal Sistem Informasi Dan Bisnis Cerdas (SIBC) Vol, 12(2).

Kusumawati, D., Faktasari, D., & Redjeki, S. (2019). Model Identifikasi Dini Mahasiswa Drop Out Menggunakan Dempster Shafer. Seminar Nasional Aptikom (SEMNASTIK) 2019, 0, Article 0.

Larose, D. T., & Larose, C. D. (2014). Discovering Knowledge in Data: An Introduction to Data Mining. John Wiley & Sons.

Maisharoh, T., & Ali, H. (2020). Faktor-faktor yang mempengaruhi Infrastruktur Teknologi Informasi: Keuangan, Fleksibilitas TI, dan Kinerja Organisasi. Universitas Mercu Bauna (UMB) Jakarta, 1–9.

Mulyani, E., Ismantohadi, E., & Koriah, K. (2020). Sistem Prediksi Potensi Drop Out Mahasiswa Menggunakan Rule Based System Pada Jurusan Teknik Informatika Politeknik Negeri Indramayu. Informatika, 8(1), Article 1. https://doi.org/10.36987/informatika.v8i1.1473

Nasrullah, A. H. (2018). Penerapan Metode C4.5 untuk Klasifikasi Mahasiswa Berpotensi Drop Out. ILKOM Jurnal Ilmiah, 10(2), 244–250. https://doi.org/10.33096/ilkom.v10i2.300.244-250

Nuraeni, F., Kurniadi, D., & Fauzian Dermawan, G. (2023). Pemetaan Karakteristik Mahasiswa Penerima Kartu Indonesia Pintar Kuliah (KIP-K) menggunakan Algoritma K-Means++. Jurnal Sisfokom (Sistem Informasi Dan Komputer), 11(3), 437–443. https://doi.org/10.32736/sisfokom.v11i3.1439

Nurhayati, S., Kusrini, K., & Luthfi, E. T. (2015). PREDIKSI MAHASISWA DROP OUT MENGGUNAKAN METODE SUPPORT VECTOR MACHINE. SISFOTENIKA, 5(1), Article 1. https://doi.org/10.30700/jst.v5i1.25

Nurjayadi, N., Andesa, K., Nasution, T., & Herwin, H. (2020). Peringatan Dini Masa Studi Dan IPK Mahasiswa Berbasis Framework For Application Of System Thinking. Jurnal Teknologi Dan Open Source, 3(2), Article 2. https://doi.org/10.36378/jtos.v3i2.738

Pakaya, K., Amali, L. N., & Padiku, I. R. (2023). Sistem Informasi Klasifikasi Mahasiswa Berpotensi Drop Out Menggunakan Algoritma C 4.5. Diffusion: Journal of Systems and Information Technology, 3(1), Article 1. https://doi.org/10.37031/diffusion.v3i1.18670

Purba, W., Tamba, S., & Saragih, J. (2018). The effect of mining data k-means clustering toward students profile model drop out potential. Journal of Physics: Conference Series, 1007(1), 012049.

Putra, A. (2017). Solusi Prediksi Mahasiswa Drop Out Pada Program Studi Sistem Informasi Fakultas Ilmu Komputer Universitas Bina Darma. Simetris: Jurnal Teknik Mesin, Elektro Dan Ilmu Komputer, 8(1), 177–184. https://doi.org/10.24176/simet.v8i1.893

Ramadhani, R. D., & Ak, D. J. (2019). Evaluasi K-Means dan K-Medoids Pada Dataset Kecil. SNIA (Seminar Nasional Informatika dan Aplikasinya), 3, D 20-24.

Riyadhi, M. F. (2019). Aplikasi Text Mining Untuk Automasi Penentuan Tren Topik Skripsi Dengan Metode K-Means Clustering (Studi Kasus: Prodi Sistem Komputer) [PhD Thesis]. Universitas Komputer Indonesia.

Samasil, S., Yuyun, Y., & Hazriani, H. (2022). Klasifikasi Mahasiswa Berpotensi Drop Out Menggunakan Algoritma Naive Bayes Dan Decision Tree. Jurnal Ilmiah Ilmu Komputer Fakultas Ilmu Komputer Universitas Al Asyariah Mandar, 8(2), Article 2. https://doi.org/10.35329/jiik.v8i2.242

Saxena, P. S., & Govil, M. C. (2009). Prediction of student’s academic performance using clustering. National Conference on Cloud Computing & Big Data, 1–6.

Vhallah, I., Sumijan, S., & Santony, J. (2018). Pengelompokan Mahasiswa Potensial Drop Out Menggunakan Metode Clustering K-Means. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 2(2), 572–577. https://doi.org/10.29207/resti.v2i2.308

W, N. R., Defiyanti, S., & Jajuli, M. (2015). Implementasi Algoritma K-Means Dalam Pengklasteran Mahasiswa Pelamar Beasiswa. Jurnal Ilmiah Teknologi Infomasi Terapan, 1(2), Article 2. https://doi.org/10.33197/jitter.vol1.iss2.2015.56

Warnars, S. (2010). Tata kelola database perguruan tinggi yang optimal dengan data warehouse. ArXiv Preprint ArXiv:1006.1663.

Downloads

Published

2023-04-02

Issue

Vol. 14 No. 2 (2023): April

Section

Articles

License

In submitting the manuscript to the journal, the authors certify that:

  1. Authors are authorized by their co-authors to enter into these arrangements.
  2. The work described has not been formally published before, except in the form of an abstract or as part of a published lecture, review, thesis, or overlay journal. Please also carefully read Publication Ethics
  3. That it is not under consideration for publication elsewhere,
  4. That its publication has been approved by all the author(s) and by the responsible authorities – tacitly or explicitly – of the institutes where the work has been carried out.
  5. Authors secure the right to reproduce any material that has already been published or copyrighted elsewhere.
  6. Authors agree to the following copyright agreement.

Authors who publish with Paedagoria : Jurnal Kajian, Penelitian dan Pengembangan Kependidikan agree to the following terms:

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal. 
  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
  3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.