Abstract

The increasing dropout rates in higher education institutions underscore the critical need for proactive strategies to identify academically at-risk students. This study presents the development and evaluation of a predictive analysis model leveraging machine learning—specifically the Random Forest algorithm—to accurately identify students at risk of academic failure. The model integrates both academic indicators (e.g., GPA, attendance, exam scores) and non-academic factors (e.g., socio-economic status, behavioral patterns, family dynamics) to provide a holistic assessment of student performance. A dataset of 100,256 student records from the Australian Student Performance Dataset was preprocessed, with key features selected to enhance model accuracy. The model achieved a predictive accuracy of 69% and was deployed through a web-based application developed using the Flask framework. Functionality includes real-time prediction, risk classification, and user-friendly visualization. Stakeholder evaluation involving 40 respondents showed 88% user satisfaction, confirming the system’s reliability, usability, and practical value. The findings demonstrate the model’s effectiveness in enabling early interventions, thereby contributing to reduced attrition rates and more inclusive, data-informed educational practices.

References

• Ansa, J. (2018). 10 causes of poor academic performance in school – Most students never admit. EduAnsa. https://www.eduansa.com/10-causes-of-poor-academic-performance-in-school-most-students-never-admit-8/#google_vignette
• Chapman, C., Laird, J., & KewalRamani, A. (2010). Trends in high school dropout and completion rates in the United States: 1972–2008 (NCES 2011-012). National Center for Education Statistics. https://files.eric.ed.gov/fulltext/ED513692.pdf
• Chen, Y., Zhang, K., & Liu, X. (2019). Identifying at-risk students based on the phased prediction model. Knowledge and Information Systems, 61(3), 1277–1297. https://link.springer.com/article/10.1007/s10115-019-01374-x
• Eyman, A., Al-Khalifa, H., & Al-Salman, A. (2020). Predicting academic success in higher education: Literature review and best practices. International Journal of Educational Technology in Higher Education, 17, Article 52. https://educationaltechnologyjournal.springeropen.com/articles/10.1186/s41239-020-0177-7
• Glavin, C. (n.d.-c). The risk factor of high school dropouts. K12 Academics. https://www.k12academics.com/High%20School%20Dropouts/risk-factor-high-school-dropouts
• Jayaprakash, S., Sharma, P., & Gupta, R. (2020). Predicting students academic performance using an improved random forest classifier. 2020 IEEE International Conference on Teaching, Assessment, and Learning for Engineering (TALE). https://ieeexplore.ieee.org/abstract/document/9167547
• Laoshi. (2024). Australian student performance dataset. Kaggle. https://www.kaggle.com/datasets/nasirayub2/australian-student-performancedata-aspd24/data?select=Australian_Student_PerformanceData+%28ASPD24%29.csv
• Lim, J. (2023). Exploring the relationships between interaction measures and learning outcomes through social network analysis: The mediating role of social presence. International Journal of Educational Technology in Higher Education, 20(1), Article 27. https://educationaltechnologyjournal.springeropen.com/articles/10.1186/s41239-023-00384-8
• Murain, I. O., & Olatunji, O. O. (n.d.). Decision tree algorithm use in predicting students’ academic performance in advanced programming course. International Journal of Higher Education and Pedagogy. https://www.diamondopen.com/journals/index.php/ijhep/article/download/274/142
• Ng, K., Hoo, M.-H., Nair, M., & Khor, K.-C. (2023). Predicting student performance in final year project using data mining classification techniques. ResearchGate. https://www.researchgate.net/publication/370961886_Predicting_student_performance_in_final_year_project_using_data_mining_classification_techniques
• Qushem, U. B., Khan, H. U., & AlGhamdi, J. (2023). Unleashing the power of predictive analytics to identify at-risk students in computer science. Technology, Knowledge and Learning. https://link.springer.com/article/10.1007/s10758-023-09674-6
• Sarao, Z. (2023, October 11). Dropout rate in universities, colleges at 35.15% in SY 2023-2024, says CHEd. INQUIRER.net. https://newsinfo.inquirer.net/1839954/dropout-rate-in-universities-colleges-at-35-15-in-sy-2023-2024-says-ched
• Srinivas, K., Raghunathan, R., & Parthiban, L. (2018). Predicting the academic performance of middle- and high-school students using machine learning algorithms. Education and Information Technologies, 27, 11355–11378. https://www.sciencedirect.com/science/article/pii/S2590291122001115
• U.S. Department of Education, National Center for Education Statistics. (2010). American Community Survey (ACS) 2010. https://nces.ed.gov/fastfacts/display.asp?id=16
• Whitcomb, K., Robbins, M. W., & Flaster, A. (2021). Not all disadvantages are equal: Racial/ethnic minority students have largest disadvantage among demographic groups in both STEM and non-STEM GPA. AERA Open, 7, 23328584211059823. https://journals.sagepub.com/doi/full/10.1177/23328584211059823