Monitoring and Predicting Performance of Students in Degree Programs using Machine Learning

Kumar G.S.; De La Cruz-Camaco D.; Ravichand M.; Joshi K.; Gupta Z.; Gupta S. · Proceedings of the 17th INDIACom; 2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023 (2023)

Resumen

In higher education, it is frequently necessary to find a solution to the issue of student retention. Managers and scholars in the field frequently rely entirely and expertise to recognise potential risk factors and students. This study looks at the research on the approaches and metrics being used now in learning analytics. While there are techniques available, our research shows that they are not focused on identifying difficult pupils as soon as possible. With the use of contemporary computer vision tools and methodologies, we design a novel statistical tool for class participation and develop a predictive model. It shows how pupils may be identified with 97% accuracy as early about week three. Additionally, we place this finding in a suitable pedagogical framework to support its application as a component of a more complete student assistance system. There is a wealth of publicly available learning data that can be utilised to analyse individual student behaviour, address their issues, improve the instructional climate, and enable data-driven choices, thanks to the support of software learning platforms. Based on that, the paper focuses on developing a system that can effectively monitor and predict the performance of students in degree programs by using the evolving machine learning. As retention of students has becoming a serious concern, it was necessary to develop performance monitoring and predicting system. Using a comprehensive research methodology this study has analysed all relevant information to the topic to draw an effective conclusion at the end.

Instituciones: Universidad Tecnológica del Perú