Application of Machine Learning Algorithms and Mathematical Modelling to Optimise University Learning Analytics

Data-driven insights play a pivotal role in optimising learning analytics within higher educationinstitutions. Despite their importance, much of the data in these institutions remains untapped,trapped in siloed data stores. This study addresses this challenge by applying machine learningand mathematical modelling using a learning analytics research framework (Khalil et al.,2022), encompassing phases of data insights, analytics, and intervention. The study aimed toidentify features influencing learner progression and discover student groups in educationalenvironments. Utilising data from 1,017 students over a 3-year period, the research employedunsupervised machine learning techniques and automated student feedback. Feature analysisidentified attendance, interactions, time intervals, and activities related to quizzes andworkshops as useful predictors of students requiring additional support. K-means modelperforms best with an average recall of 89% and an overall accuracy of 72% for identifying atrisk student groups using non-personally identifying data.The findings emphasise the utility of unsupervised machine learning for early identification ofat-risk students, enabling timely interventions to prevent potential failure or dropout.Personalised and automated feedback forms summarising students’ progression received highratings, 93% rating for usefulness from students, highlighting their satisfaction with it as alearning analytics intervention. Insights highlight the importance of data quality, personalisedfeedback, and transparent communication with learners. Challenges, such as automatingfeedback and scalability, are addressed, along with the necessity of leveraging non-personallyidentified data to mitigate bias.The incorporation of a data science approach, enriched by machine learning, holds the potentialto provide stakeholders with enriched insights, boost student engagement, and enhance overallstudent outcomes. This study will extend the body of knowledge of how machine learningmodelling can be used to foster and promote student success in higher education.