Perbandingan Akurasi Algoritma C4.5 dan K-NN Untuk Prediksi Kelulusan Mahasiswa Penerima Beasiswa
DOI:
https://doi.org/10.70052/jka.v3i1.623Keywords:
Beasiswa, Klasifikasi, C4.5, K-Nearest NeighborAbstract
Penelitian ini bertujuan untuk menganalisis permasalahan yang dihadapi oleh Administrator Universitas dalam pengambilan keputusan penerima beasiswa. Metode yang digunakan melibatkan pemrograman dinamis untuk menggantikan pendekatan tradisional yang masih sering digunakan. Penelitian ini berfokus pada perbandingan performa antara algoritma Decision Tree (C4.5) dan K-Nearest Neighbor (K-NN) dalam mengklasifikasikan data penerima beasiswa. Data yang diperoleh adalah sekunder, yaitu data historis penerima beasiswa yang telah dikumpulkan oleh pihak universitas. Tahapan penelitian dimulai dari pengumpulan dan pra-pemrosesan data, diikuti dengan penerapan algoritma C4.5 dan K-NN, serta evaluasi performa algoritma menggunakan metrik seperti akurasi, presisi, recall, dan AUC. Berdasarkan hasil pengujian, algoritma Decision Tree (C4.5) menunjukkan akurasi sebesar 74,95%, presisi 20,9%, recall 77,1%, dan AUC sebesar 0,752. Sementara itu, algoritma K-Nearest Neighbor hanya mencapai akurasi 71,79%, presisi 39,0%, recall 45,3%, dan AUC sebesar 0,734. Dengan demikian, algoritma Decision Tree (C4.5) memiliki performa yang lebih baik dalam menyelesaikan permasalahan klasifikasi ini dibandingkan algoritma K-Nearest Neighbor.
This research aims to analyze the problems faced by University Administrators in making decisions about scholarship recipients. The method used involves dynamic programming to replace the traditional approach which is still often used. This research focuses on the performance comparison between the Decision Tree (C4.5) and K-Nearest Neighbor (K-NN) algorithms in classifying scholarship recipient data. Data was obtained from secondary sources, specifically historical records of scholarship recipients. Based on test results, the Decision Tree algorithm (C4.5) shows an accuracy of 74.95%, precision of 20.9%, recall of 77.1%, and AUC of 0.752. Meanwhile, the K-Nearest Neighbor algorithm only achieved 71.79% accuracy, 39.0% precision, 45.3% recall, and an AUC of 0.734. Thus, the Decision Tree algorithm (C4.5) performs better in solving this classification problem than the K-Nearest Neighbor algorithm.
References
B. Harpad, M. Fahmi, P. Pahrudin, and R. Andrea, “Pengelompokan Siswa Layak Penerima Beasiswa dengan Menerapkan Algoritma K-Means Clustering Data Mining,” J. Media Inform. Budidarma, vol. 8, no. 2, p. 913, 2024, doi: 10.30865/mib.v8i2.7394.
I. Arfyanti, M. Fahmi, and P. Adytia, “Penerapan Algoritma Decision Tree Untuk Penentuan Pola Penerima Beasiswa KIP Kuliah,” Build. Informatics, Technol. Sci., vol. 4, no. 3, pp. 1196–1201, 2022, doi: 10.47065/bits.v4i3.2275.
A. Purwanto, “Analisa Perbandingan Kinerja Algoritma C4.5 Dan Algoritma K-Nearest Neighbors Untuk Klasifikasi Penerima Beasiswa,” J. Teknoinfo, vol. 14, pp. 48–58, 2020.
D. H. H. S. Kamagi, “Implementasi Data Mining dengan Algoritma C4.5 untuk Memprediksi Tingkat Kelulusan Mahasiswa,” Proc. - 2016 IEEE Int. Power Electron. Motion Control Conf. PEMC 2016, vol. VI, no. 1, pp. 254–260, 2014, doi: 10.1109/EPEPEMC.2016.7752007.
R. Hadi, I. G. A. Desi Saryanti, and I. G. N. Ady Kusuma, “Implementasi Aplikasi Sederhana Dengan Klasifikasi Penjualan Berbasis K-Nearest Neighbor Pada Aplikasi Desktop,” J. Innov. Res. Knowl., vol. 1, no. 9, pp. 1–8, 2022.
J. C. Mestika, M. O. Selan, and M. I. Qadafi, “Menjelajahi Teknik-Teknik Supervised Learning untuk Pemodelan Prediktif Menggunakan Python,” Bul. Ilm. Ilmu Komput. dan Multimed., vol. 1, no. 1, pp. 216–219, 2023.
N. Khansa and Z. Fatah, “Gudang Jurnal Multidisiplin Ilmu Analisis Perbandingan Algoritma Machine Learning Dalam Klasifikasi Gangguan Tidur,” vol. 2, no. November, pp. 76–81, 2024.
I. H. Witten and E. Frank, Data Mining Practical Machine Learning Tools and Techniques. 2005.
M. R. Anugrah, N. A. Al-Qadr, N. Nazira, and N. Ihza, “Implementation of C4.5 and Support Vector Machine (SVM) Algorithm for Classification of Coronary Heart Disease,” Public Res. J. Eng. Data Technol. Comput. Sci., vol. 1, no. 1, pp. 20–25, 2023, doi: 10.57152/predatecs.v1i1.805.
B. Charbuty and A. Abdulazeez, “Classification Based on Decision Tree Algorithm for Machine Learning,” J. Appl. Sci. Technol. Trends, vol. 2, no. 01, pp. 20–28, 2021, doi: 10.38094/jastt20165.
I. D. Mienye, Y. Sun, and Z. Wang, “Prediction performance of improved decision tree-based algorithms: A review,” Procedia Manuf., vol. 35, pp. 698–703, 2019, doi: 10.1016/j.promfg.2019.06.011.
A. Cherfi, K. Nouira, and A. Ferchichi, “Very Fast C4.5 Decision Tree Algorithm,” Appl. Artif. Intell., vol. 32, no. 2, pp. 119–137, 2018, doi: 10.1080/08839514.2018.1447479.
F. Musa, F. Basaky, and O. E.O, “Obesity prediction using machine learning techniques,” J. Appl. Artif. Intell., vol. 3, no. 1, pp. 24–33, 2022, doi: 10.48185/jaai.v3i1.470.
H. Rajaguru and S. R. Sannasi Chakravarthy, “Analysis of decision tree and k-nearest neighbor algorithm in the classification of breast cancer,” Asian Pacific J. Cancer Prev., vol. 20, no. 12, pp. 3777–3781, 2019, doi: 10.31557/APJCP.2019.20.12.3777.
S. Uddin, I. Haque, H. Lu, M. A. Moni, and E. Gide, “Comparative performance analysis of K-nearest neighbour (KNN) algorithm and its different variants for disease prediction,” Sci. Rep., vol. 12, no. 1, pp. 1–11, 2022, doi: 10.1038/s41598-022-10358-x.
F. Tempola, M. Muhammad, and A. Khairan, “Perbandingan Klasifikasi Antara KNN dan Naive Bayes pada Penentuan Status Gunung Berapi dengan K-Fold Cross Validation,” J. Teknol. Inf. dan Ilmu Komput., vol. 5, no. 5, pp. 577–584, 2018, doi: 10.25126/jtiik.201855983.
A. Sucipto, “Credit Prediction With Neural Network Algorithm,” Pros. Semin. Nas. Multi Disiplin Ilmu Call Pap. Unisbank, vol. 978-979–36, no. 15, pp. 1–10, 2012.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Andrian Fakih, Mohammad Alfi Hamzami, Muhammad Raihan Hadianto, Najdah Ibtisamah Shafira Alifah (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
