Learning Management Systems (LMSs) driven by artificial intelligence are causing a transformative change in the educational sector. This study aims to explore their impact on the teaching and learning processes inside higher education. The study deploys a mixed method of qualitative and quantitative approaches to understand the current applications and AI-LMS advantages. This research uses qualitative analysis to discover key themes in student performance, learning problems, and interventions. Quantitative analysis will be conducted using the Paradis corpus consisting of naturalistic language samples from 25 children learning English, using descriptive, category, correlation, and inferential statistics. Machine learning algorithms will be utilized to classify and predict student performance. The study's novelty lies in the combination of quantitative and qualitative methods to provide evidence-based suggestions for addressing challenges detected in student performance. The study suggests deploying advanced algorithms for machine learning and qualitative interviews to improve the accuracy of predicting models for student achievement. This might include engaging an extensive range of participants from varying origins and educational contexts.

Learning Management Systems, Artificial intelligence, Teaching, Learning, Higher Education, student performance.