Outlier Analysis of Student Academic Performance Data using the Local Outlier Factor (LOF) Method

Made Pasek Agus Ariawan, Ni Putu Eka Apriyanthi, Ida Bagus Adisimakrisna Peling

Abstract


The digital transformation of the higher education sector has led to the accumulation of massive and increasingly complex academic datasets. One of the main challenges in managing these data is the presence of outliers or anomalies, which may reflect exceptional cases, such as students with outstanding potential or those at risk of academic failure. This study aims to implement the Local Outlier Factor (LOF) algorithm to analyze outliers in student academic performance profiles. The research methodology involved collecting data from 82 students, comprising Grade Point Average (GPA), programming test scores, and project scores; preprocessing the data using Min-Max Scaling; applying the LOF algorithm with a 90th-percentile threshold; evaluating parameter sensitivity across eight values of K (ranging from 10 to 80); and performing three-dimensional (3D) visualization. The results demonstrate that the LOF method is effective in identifying local outliers that may not be detected by conventional methods. Among the 82 students analyzed, LOF identified 9 outliers (10.98% of the total sample) at the optimal K value of 20, six of which were not detected by the Z-score method. Further analysis revealed patterns of competency imbalance, including students with high GPAs and programming test scores but relatively low project scores. Parameter evaluation indicated that selecting an optimal K (number of neighbors) is crucial for maintaining a balance between detection sensitivity and algorithmic stability in the presence of data noise. In practical terms, the findings can support academic departments in developing early warning systems for students at risk of academic failure, identifying high-potential students for academic mentoring or scholarship opportunities, and evaluating the alignment between formal academic achievements and practical competencies.

Keywords


3D visualization; academic profile; data anomaly; local outlier factor; student

Full Text:

PDF

References


Vrantika Br Samosir, Agung Mulyo Widodo, Nizirwan Anwar, Binastya Anggara Sekti, and Nixon Erzed, “Identifikasi Outlier menggunakan Teknik Data Mining Clustering untuk Analisis Data Tracer Study pada Fakultas Ilmu Komputer Universitas Esa Unggul,” IKRA-ITH Informatika : Jurnal Komputer dan Informatika, Vol. 8, No. 1, pp. 162–174, Mar. 2024, DOI: 10.37817/ikraith-informatika.v8i1.3211.

Jovita and S. Susanto, “Perbandingan Metode IQR vs Isolation Forest dalam Deteksi Outlier pada Data Klaim Asuransi di PT Askrindo Cabang Semarang Comparison of IQR and Isolation Forest Methods for Outlier Detection in Insurance Claim Data at PT Askrindo Semarang Branch,” Jurnal Transformatika, Vol. 23, pp. 268–277, Jan. 2026, DOI: 10.26623/transformatika.v23i2.13726.

M. Khoiron, “Pemanfaatan K-Means Clustering dalam Melihat Innovation Mindset Mahasiswa STIMIK ESQ menggunakan Model Berkeley Innovation Index,” 2017. DOI: 10.13140/RG.2.2.26337.81763.

P. A. Ariawan, “Optimasi Pengelompokan Data pada Metode K-Means dengan Analisis Outlier,” Jurnal Nasional Teknologi dan Sistem Informasi, Vol. 5, No. 2, pp. 88–95, Sep. 2019, DOI: 10.25077/teknosi.v5i2.2019.88-95.

W. Yustanti, “Studi Komparasi Local Outlier Factor (LOF) dan Isolation Forest (IF) pada Analisis Anomali Kinerja Dosen,” Journal of Informatics and Computer Science, Vol. 06, 2024.

A. K. Jailani and A. Erna, “Deteksi Anomali pada Rasio Jam Belajar dan Aktivitas Sosial terhadap Performa Akademis Mahasiswa menggunakan Metode Local Outlier Factor (LOF),” SISITI : Seminar Ilmiah Sistem Informasi dan Teknologi Informasi, Vol. 14, No. 1, pp. 79–88, Mar. 2025, DOI: 10.36774/sisiti.v14i1.1678.

estannisa asfarina fadlilah, “Identifikasi Anomali Data Akademik menggunakan Dbscan Outlier Detection,” Prosiding Seminar Nasional Sains dan Teknologi, Vol. 12, No. 1, pp. 336–342, Nov. 2022, DOI: 10.36499/psnst.v12i1.7012.

P. Satya Saputra, “Analisis Prediktif Dropout Mahasiswa berdasarkan Kinerja Akademik Semester Awal menggunakan Machine Learning,” Jurnal Riset dan Aplikasi Mahasiswa Informatika (JRAMI), Vol. 07, 2026.

M. P. A. Ariawan, I. B. A. Peling, and G. B. Subiksa, “Prediksi Nilai Akhir Matakuliah Mahasiswa menggunakan Metode K-Means Clustering (Studi Kasus : Matakuliah Pemrograman Dasar),” Jurnal Nasional Teknologi dan Sistem Informasi, Vol. 9, No. 2, 2023, DOI: 10.25077/teknosi.v9i2.2023.122-131.

Y. Zhou, H. Xia, D. Yu, J. Cheng, and J. Li, “Outlier Detection Method based on High-Density Iteration,” Inf. SCI. (N. Y)., Vol. 662, p. 120286, 2024, DOI: https://doi.org/10.1016/j.ins.2024.120286.

R. Tatikonda, R. Thatikonda, S. M. Potluri, R. Thota, V. S. Kalluri, and A. Bhuvanesh, “Data-Driven Store Design: Floor Visualization for Informed Decision Making,” in 2025 International Conference in Advances in Power, Signal, and Information Technology (APSIT), 2025, pp. 1–6. DOI: 10.1109/APSIT63993.2025.11085151.

N. Sa’adah, T. Andiansyah, T. Hidayat, C. Amni, and S. Sunyanti, “Analisis Distribusi dan Tren Nilai Mahasiswa dengan Pendekatan Statistik Deskriptif dan Visualisasi Data,” sudo Jurnal Teknik Informatika, Vol. 4, No. 3, pp. 203–211, Sep. 2025, DOI: 10.56211/sudo.v4i3.1233.

A. Pily, Susanti, U. Rio, and Tashid, “Komparasi K-Means Clustering dengan Euclidean dan Cosine Similarity untuk Segmentasi dan Rekomendasi Produk pada Data E-Commerce,” The Indonesian Journal of Computer Science, Vol. 14, Apr. 2025, DOI: 10.33022/ijcs.v14i2.4713.

Nathanael Kenneth Lay, Desi Arisandi, and Henoch Juli Christanto, “Analisa Perbandingan Algoritma K-Means dan DBSCAN untuk Klastering Wilayah Rawan Bencana,” in Building of Informatics, Technology and Science (BITS), Dec. 2025, p. 18751886.

M. M. Breunig, H.-P. Kriegel, R. T. Ng, and J. Sander, “LOF: Identifying Density-based Local Outliers,” ACM SIGMOD Record, Vol. 29, No. 2, pp. 93–104, Jun. 2000, DOI: 10.1145/335191.335388.

F. Pedregosa et al., “Scikit-Learn: Machine Learning in Python,” Journal of Machine Learning Research, Vol. 12, pp. 2825–2830, 2011.

F. T. Liu, K. M. Ting, and Z.-H. Zhou, “Isolation Forest,” in 2008 Eighth IEEE International Conference on Data Mining, 2008, pp. 413–422, DOI: 10.1109/ICDM.2008.17.

M. Ester, H.-P. Kriegel, J. Sander, and X. Xu, “A Density-based Algorithm for Discovering Clusters in Large Spatial Databases with Noise,” in Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining (KDD-96), 1996, pp. 226–231.




DOI: https://doi.org/10.32520/stmsi.v15i11.6408

Article Metrics

Abstract view : 0 times
PDF - 0 times

Refbacks

  • There are currently no refbacks.


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