Student Information System for Computer Studies with Integrated Programming Anxiety Level Prediction and Balanced Group Recommendations

Programming anxiety is a recognized challenge in computer studies, often affecting students’ academic performance and retention. Addressing this issue requires a structured and technology-driven approach that enables faculty to identify at-risk students and implement targeted academic interventions. This study aimed to provide a solution by developing a web-based system that integrates predictive analytics to support decision-making. Specifically, it incorporated a pre-developed machine learning- based prediction model, automate student group formation using a custom heterogeneous algorithm, and featured a data visualization dashboard for faculty analysis. The system was developed using the Spiral Model to ensure iterative improvements and was evaluated based on the ISO/IEC 25010 Software Quality Model, focusing on key software quality attributes. Expert evaluation of the system’s performance resulted in a grand mean score of 3.70, indicating strong quality across all metrics. The findings demonstrate that the developed system effectively integrates predictive analytics to assist higher education institutions in addressing programming anxiety. By enabling real-time identification of at-risk students and facilitating structured academic support, the system contributes to the fields of educational technology and learning analytics, offering a scalable solution for improving student outcomes in computing education.