Previous research has shown a strong correlation between class attendance and pass rates among mathematics students. Building on these findings, this study presents the development of a data-informed early warning system designed to identify students at academic risk following their first major test. Using predictive modeling techniques implemented in SPSS, the system analyzes attendance records and initial test scores to estimate the likelihood of academic failure. The paper outlines the rationale, structure, and prototype of the model, with simulated outputs used to demonstrate its potential. The system is currently being tested, and full results will be presented in the final paper. This work contributes a practical framework for supporting timely intervention and promoting equitable learning outcomes in mathematics.

Authors:
Bonani Sibanda, Vaal University of Technology, South Africa
Sihle Moyo, Vaal University of Technology, South Africa

About the Presenter(s)
Dr Bonani Sibanda is a Senior lecturer in the Department of Mathematics at Vaal University of Technology. She likes solving students problems. She has a great passion with lecturing , discovering students' weaknesses and helping them.

See this presentation on the full schedule – Thursday Schedule

Bookmark