A five-member student team from the Department of Computer Science at the Kwame Nkrumah University of Science and Technology (KNUST) has won the Best Presenter Award (Parallel Session) at the 10th International Undergraduate Research Conference (IURC 2026).
The conference was hosted virtually by Universiti Teknologi Malaysia (UTM).
The KNUST students received the award for presenting EduTrace, an explainable early-warning system developed to help identify pupils at risk of dropping out of rural Junior High Schools in Ghana.
The team, from the CAN-DO Virtual Lab, comprised Manuel Bartimeus, Team Lead and Presenter; Richeal Pokuah; Wisdom Oti; Jeffrey Antwi; and David Karikari. Their project was supervised by Dr Eric Opoku Osei of KNUST’s Department of Computer Science.
EduTrace was developed to address some of the practical challenges associated with deploying machine-learning systems for predicting school dropout in rural and low-connectivity communities.
Unlike systems that depend on smartphones, reliable internet connectivity and digital dashboards, EduTrace is designed to work with information obtainable from ordinary paper-based school registers and communicate alerts through basic SMS.
Central to the system is an approach the researchers describe as SHAP-to-SMS, which converts the reasoning behind a pupil’s dropout-risk prediction into a single 160-character text message.
The message can be transmitted over a 2G network without requiring an internet connection or smartphone application, potentially making the technology more accessible to schools in resource-constrained communities.
EduTrace uses six variables obtainable from ordinary school registers and applies machine-learning techniques to identify pupils who may require early intervention.
As part of the study, the researchers evaluated 428 student-year records involving 180 pupils between 2024 and 2026 before testing the system on 248 records it had not previously encountered. The test dataset contained seven recorded dropout cases.
At the researchers’ selected operating point, EduTrace identified more genuine dropout cases than an untuned baseline, while all alerts produced by the system remained within the limit of a single GSM text message.
The student researchers, however, acknowledged limitations in their findings, noting that the system’s ability to rank genuinely at-risk pupils above others was not statistically distinguishable from chance.
The researchers therefore presented EduTrace as a decision-support tool rather than a replacement for educational decision-making, particularly for schools where internet-dependent early-warning systems may not be practical.
The Best Presenter Award at IURC 2026 recognises the KNUST students’ presentation of the research and its potential application to an educational challenge affecting rural communities in Ghana.
No Comment! Be the first one.