Machine Learning-Based Prediction of Algerian University Student Participation in Sports Activities

Aug 3, 2026

Upload by Riley

Student participation in university sports is shaped by individual, social, cultural, and institutional influences. Even with the well-established health and developmental benefits of sport, many Algerian students encounter barriers such as academic workload and insufficient facilities. This study presents a machine learning framework to predict sports participation, emphasizing key determinants including gender and prior athletic background. Logistic regression and decision tree models identify participation patterns and the most attractive sport disciplines, supporting inclusive policy design, resource planning, and tailored university programs.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Introduction

Background and problem statement

Rationale for machine learning approach

Methodology

Data description (Algerian University Sports Dataset)

MACHINE LEARNING-BASED PREDICTION OF ALGERIAN UNIVERSITY STUDENT PARTICIPATION IN SPORTS ACTIVITIES Mohamed Amine DAOUD1*, Abdelkader BOUGUESSA1, Kamel BENDDINE 2 Article history: Received: 2024 November 07; Revised 2025 January 20; Accepted 2025 January 22; Available online: 2025 February 10; Available print: 2025 February 28 ©2024 Studia UBB Educatio Artis Gymnasticae. Published by Babeş-Bolyai University. This work is licensed under a Creative Commons AttributionNonCommercial-NoDerivatives 4.0 International License ABSTRACT. Student participation in university sports is influenced by individual, social, cultural, and institutional factors. Despite the recognized benefits of sports, many students face barriers such as academic pressures and inadequate infrastructure. This study proposed a machine learning-based approach to predict sports participation among Algerian university students, focusing on identifying key factors like gender and athletic background to guide inclusive sports policies. Using models like logistic regression and decision trees, the study effectively predicted participation patterns and highlighted the most attractive sports disciplines, enabling better resource planning and tailored programs. This approach offers valuable insights for fostering a dynamic, inclusive sports ecosystem and emphasizes the potential of machine learning to enhance university sports management. Keywords: Sport; University; Prediction; Activity; Algeria INTRODUCTION Universities play a central role in the socialization of students by creating an environment where exchanges and social interactions are encouraged, particularly through sports activities. By offering opportunities to practice 1 LRIAS Lab, Dept. of Computer Sciences, Ibn-Khaldoun University of Tiaret, Algeria 2 CEHM Lab, El-Bayedh University Center, Algeria * [Corresponding author: k.beneddine@cu-elbayadh.dz](Corresponding author: k.beneddine@cu-elbayadh.dz) various sports, higher education institutions aim not only to improve students’physical health but also to foster essential skills for their social development, such as teamwork, discipline, and respect for others (Bailey et al., 2013, Stodolska, al. ,2015). These activities, which are an integral part of the university experience, contribute to the development of social awareness by enabling students to become familiar with cooperation and community involvement. Universities sports will ensure the alignment of athletic achievements with the goal of enhancing the physical potential of younger generations through physical exercise, which is the primary and most effective means for this transformation. University sports hold a crucial place in the academic and social journey of students, playing a vital role in their physical, mental, and social development (Eime, 2013) . Within universities, sports are not merely leisure activities; they are a powerful tool for fostering social cohesion, personal discipline, and student well-being. In Algeria, where universities welcome a growing influx of students each year, sports participation remains limited to a small number of participants and disciplines. This situation highlights a significant challenge: despite access to sports facilities and the well-known benefits of physical activity, a low proportion of students engage in the sports activities offered. This issue leads us to explore the reasons behind this limited participation and the factors that influence students’ decisions to become involved, or not, in university sports. It is therefore relevant to conduct an in-depth study to analyze students' sports habits, understand perceived motivations and obstacles, and ultimately predict students' participation profiles. By identifying these factors, this research aims to contribute to the development of tailored strategies that encourage broader and more inclusive sports participation within Algerian universities, thereby enabling student

FAQs

Which factors does the study focus on to predict Algerian university students’ sports participation?

The study highlights factors such as gender and athletic background, and it frames the prediction using variables like age, preferences for disciplines, and perceived benefits of sport.

Why are machine learning techniques suitable for this research?

Machine learning enables analysis of large datasets to uncover hidden patterns, trends, and correlations that may not be visible using traditional data collection and analysis approaches.

What models are used and what outputs support university sports management?

The study uses models such as logistic regression and decision trees to predict participation patterns and identify the sports disciplines most attractive to students, informing resource planning and tailored programs.

Aug 3, 2026

Upload by Riley