Pengembangan Sistem Informasi Prediksi Risiko Dropout Mahasiswa Berbasis Web Menggunakan Algoritme CatBoost
Abstract
The problem addressed was the limited use of dropout prediction models, which had generally focused on algorithm performance and had not been integrated into an academic monitoring system design.This study aimed to develop a web-based prototype information system for predicting student dropout risk using the CatBoost algorithm to support academic monitoring. The development method used was Prototyping, while the prediction model was built from the Predict Students Dropout and Academic Success dataset, which was reduced to 3,399 records with two classes, namely dropout and graduate. The results showed that the developed prototype included manual prediction, CSV import, prediction monitoring, and role-based reporting features. The CatBoost model achieved 90.29% accuracy, 85.33% precision, 88.76% recall, and 87.01% F1-score. These findings indicated that the prototype had the potential to serve as a basis for developing an early detection system for students at risk of dropout. Keywords: Academic monitoring; CatBoost; Dropout prediction; System prototype; Web-based information system
Abstrak
Permasalahan yang diangkat adalah keterbatasan pemanfaatan model prediksi dropout yang umumnya masih berfokus pada performa algoritme dan belum terintegrasi ke dalam rancangan sistem pemantauan akademik. Penelitian ini bertujuan mengembangkan prototype sistem informasi prediksi risiko dropout mahasiswa berbasis web menggunakan algoritme CatBoost untuk mendukung pemantauan akademik. Metode pengembangan yang digunakan adalah Prototyping, sedangkan model prediksi dibangun dari dataset Predict Students Dropout and Academic Success yang diseleksi menjadi 3.399 data dengan dua kelas, yaitu dropout dan graduate. Hasil penelitian menunjukkan bahwa prototype yang dikembangkan memuat fitur prediksi manual, impor file CSV, monitoring hasil prediksi, dan laporan berbasis peran pengguna. Model CatBoost memperoleh accuracy 90,29%, precision 85,33%, recall 88,76%, dan F1-score 87,01%. Temuan ini menunjukkan bahwa prototype tersebut berpotensi menjadi dasar pengembangan sistem deteksi dini mahasiswa berisiko dropout.
Kata kunci: Pemantauan akademik
References
M. N. Waruwu, Y. Zega, R. N. Mendrofa, and Y. N. Telaumbanua, “Implementasi Algoritma Machine Learning Untuk Deteksi Performa Akademik Mahasiswa,” teknimedia, vol. 5, no. 2, pp. 181–186, Dec. 2024, doi: doi.org/10.46764/teknimedia.v5i2.214.
M. P. Colpo, T. Thompsen Primo, M. S. de Aguiar, and C. Cechinel, “Educational data mining for dropout prediction: Trends, opportunities, and challenges,” Rev. Bras. Inform. Na Educ., vol. 32, pp. 220–256, May 2024, doi: 10.5753/rbie.2024.3559.
D. I. Saputra and D. A. Haris, “Perancangan Business Intelligence untuk Prediksi Risiko Drop Out Mahasiswa Berdasarkan Analisis Data Historis,” J. Ekon. Manaj. Sist. Inf., vol. 7, no. 2, pp. 1572–1579, Dec. 2025, doi: doi.org/10.38035/jemsi.v7i2.6991.
C. F. de Oliveira, S. R. Sobral, M. J. Ferreira, and F. Moreira, “How does learning analytics contribute to prevent students’ dropout in higher education: A systematic literature review,” Big Data Cogn. Comput., vol. 5, no. 4, p. 64, Nov. 2021, doi: doi.org/10.3390/bdcc5040064.
M. Vaarma and H. Li, “Predicting student dropouts with machine learning: An empirical study in Finnish higher education,” Technol. Soc., vol. 76, no. 102474, p. 102474, Mar. 2024, doi: doi.org/10.1016/j.techsoc.2024.102474.
A. Villar, C. Robledo, and V. De Andrade, “Supervised machine learning algorithms for predicting student dropout and academic success : a comparative study,” Discov. Artif. Intell., vol. 4, no. 2, Jan. 2024, doi: 10.1007/s44163-023-00079-z.
D. A. Gutierrez-Pachas, G. Garcia-Zanabria, E. Cuadros-Vargas, G. Camara-Chavez, and E. Gomez-Nieto, “Supporting decision-making process on higher education dropout by analyzing academic, socioeconomic, and equity factors through machine learning and survival analysis methods in the Latin American context,” Educ. Sci., vol. 13, no. 2, p. 154, Feb. 2023, doi: doi.org/10.3390/educsci13020154.
D. Bañeres, M. E. Rodríguez-González, A.-E. Guerrero-Roldán, and P. Cortadas, “An early warning system to identify and intervene online dropout learners,” Int. J. Educ. Technol. High. Educ., vol. 20, no. 1, p. 3, Jan. 2023, doi: 10.1186/s41239-022-00371-5.
E. Nimy and M. Mosia, “applied sciences Identifying At-Risk Students for Early Intervention — A Probabilistic Machine Learning Approach,” Appl. Sci., vol. 13, no. 6, p. 3869, Mar. 2023, doi: doi.org/10.3390/app13063869.
J. Keider and G. Santacoloma, “Predictive Model to Identify College Students with High Dropout Rates Modelo predictivo para identificar estudiantes universitarios con alto grado de deserción Modelo preditivo para identificar estudantes universitários com alto risco de evasão,” SciELO, vol. 25, pp. 1–10, May 2023, doi: 10.24320/redie.2023.25.e13.5398.
A. C. M. T and A. L. R. P. J, “Ensemble Machine Learning Model for University Students ’ Risk Prediction and Assessment of Cognitive Learning Outcomes,” IJIET, vol. 13, no. 6, pp. 948–958, Jun. 2023, doi: 10.18178/ijiet.2023.13.6.1891.
S. Wang and J. He, “Evaluating and Forecasting Undergraduate Dropouts Using Machine Learning for Domestic and International Students,” technologies, vol. 13, no. 11, p. 480, Oct. 2025, doi: doi.org/10.3390/technologies13110480.
N. Kurbanazarova, P. Sethuraman, D. P, N. A. Khamitdkhanovich, Y. Mahmood Younus, and A. D. Ghate, “Student Dropout Risk Classification Using CatBoost Algorithm in Higher Education Retention Systems,” in 2025 International Conference on AI-Driven STEM Education and Learning Technologies (AISTEMEDU), Dec. 2025, pp. 1–7. doi: 10.1109/AISTEMEDU67077.2025.11403945.
E. Seo, J. Yang, J. Lee, and G. So, “Predictive modelling of student dropout risk : Practical insights from a South Korean distance university,” Heliyon, vol. 10, no. 11, p. e30960, Jun. 2024, doi: 10.1016/j.heliyon.2024.e30960.
S. Kim, E. Yoo, S. Kim, L. Palma, and O. Academy, “Associated Factor Analysis Using Machine Learning Techniques”, arXiv preprint arXiv:2310.10987, Oct. 2023, doi: 10.48550/arXiv.2310.10987.
D. Andrade-girón et al., “Predicting Student Dropout based on Machine Learning and Deep Learning : A Systematic Review,” EAI Endorsed Trans., vol. 10, no. 5, pp. 1-11, Jul. 2023, doi: 10.4108/eetsis.3586.
M. A. Hassan and A. H. Muse, “Insights from the 2022 National Education Accessibility Survey in Somaliland,” Appl. Sci. Learn., vol. 14, no. 17, p. 7593, Aug. 2024, doi: doi.org/10.3390/app14177593.
M. Cannistrà, C. Masci, F. Ieva, T. Agasisti, and A. M. Paganoni, “Early-predicting dropout of university students: an application of innovative multilevel machine learning and statistical techniques,” Stud. High. Educ., vol. 47, no. 9, pp. 1935–1956, Sep. 2022, doi: doi.org/10.1080/03075079.2021.2018415.
L. G. R. Putra, D. D. Prasetya, and M. Mayadi, “Student dropout prediction using Random Forest and XGBoost method,” INTENSIF, vol. 9, no. 1, pp. 147–157, Feb. 2025, doi: doi.org/10.29407/intensif.v9i1.21191.
B. Carballo-Mend’ivil, A. Arellano-González, N. J. R’ios-Vázquez, and M. del P. Lizardi-Duarte, “Predicting student dropout from day one: {XGBoost-based} early warning system using pre-enrollment data,” Appl. Sci., vol. 15, no. 16, p. 9202, Aug. 2025, doi: doi.org/10.3390/app15169202.
How To Cite This :
Refbacks
- There are currently no refbacks.
