International Journal of Electrical and Computer Engineering (IJECE) Vol. 15, No. 4, August 2025, pp. 4181~4191 ISSN: 2088-8708, DOI: 10.11591/ijece.v15i4.pp4181-4191  4181 Journal homepage: http://ijece.iaescore.com Gradient boosting algorithm for predicting student success Brahim Jabir 1 , Soukaina Merzouk 1 , Radoine Hamzaoui 2 , Noureddine Falih 2 1 ESIM Research Team, Polydisciplinary Faculty of Sidi Bennour, Chouaib Doukkali University, Morocco 2 Laboratory of Innovation in Mathematics and Applications and Information Technologies (LIMATI), Beni Mellal, Morocco Article Info ABSTRACT Article history: Received Sep 6, 2024 Revised Mar 25, 2025 Accepted May 23, 2025 The idea of using machine learning resolution techniques to predict student performance on an online learning platform such as Moodle has attracted considerable interest. Machine learning algorithms are capable of correctly interpreting the content and thus predicting the performance of our students. Algorithms namely gradient boosting machines (GBM) and eXtreme gradient boosting (XGBoost) are highly recommended by most researchers due to their high accuracy and smooth boosting time. This research was conducted to analyze the effectiveness of the XGBoost algorithm on Moodle platform to predict student performance by analyzing their online activities, practicing various types of online activities. The proposed algorithm was applied for the prediction of academic performance based on this data received from Moodle. The results demonstrate a strong correlation between many activities like the number of hours spent online and the achievement of academic goals, with a remarkable prediction rate of 0.949. Keywords: Distance learning E-learning Machine learning Performance prediction XGBoost algorithm This is an open access article under the CC BY-SA license. Corresponding Author: Brahim Jabir ESIM Research Team, Polydisciplinary Faculty of Sidi Bennour, Chouaib Doukkali University El Jadida, Morocco Email: ibra.jabir@gmail.com 1. INTRODUCTION Education has become a key sector of digital transformation initiatives, especially in regions that are striving to modernize their education systems to meet contemporary demands, especially in developing countries. In Morocco, we have noticed this evolution attempt which is embodied by the National Plan for Accelerating the Transformation of the Ecosystem launched in 2023, it focuses on digital learning platforms and the development of relevant technological skills [1]. This mission has led to a rapid expansion of online learning on several modules, with 70% of courses now being delivered online. These platforms generate large amounts of data, especially data on student interactions, offering unique opportunities to evaluate the educational processes of institutions and improve learning outcomes. Ethical challenges also pose major obstacles to research and this requires a rigorous approach to avoid problems of confidentiality [2]. Researchers must obtain explicit permission from administrators to access and use student data. In addition, handling this data requires meticulous attention to confidentiality and privacy protocols because the personally identifiable information must never be disclosed beyond the research team and must be used exclusively for educational purposes and remain under the supervision of the students' teachers who have the professional responsibility and understanding of the context to ensure appropriate use. Machine learning (ML) has moved beyond its original niche in computer science to become a go-to tool on the toolbox of the practitioner in a range of professions; one of them is education if we focus here, where it helps data analysis, personalized learning, and predictive modeling [3]. ML as a subfield of artificial intelligence, is concerned with the design of systems that learn from data and can adapt their performance in the face of changing conditions rather than being explicitly programmed. This ability is certainly relevant in