In recent years, the increasing focus on learning analytics (LA) and educational data mining (EDM) has driven the emergence of new methodologies and advancements in educational environments. This evolving field offers a variety of possibilities and applications, ranging from enhancing instructional design and teaching strategies based on student needs, to personalizing and adapting technology-enhanced learning (TEL) systems. Numerous studies and practices have contributed to expanding the potential of these techniques in the educational domain. By providing cutting-edge techniques for the creation and integration of more individualized, adaptable, and interactive learning environments, LA and EDM significantly improve learning processes. This study aims to enhance the educational performance of students by tailoring instructional content and strategies to their specific needs and learning styles. The framework employs data mining algorithms to analyse and extract meaningful patterns and insights from the collected data, while learning analytics tools are utilized to continuously monitor and assess students’ progress. By combining these technologies, the framework modifies learning materials and instructional approaches in real time, guaranteeing that students receive tailored assistance and support. The student’s performance is judged using pass/fail outcomes. The model’s performance is evaluated using the performance metrics, which include sensitivity, specificity, accuracy, and the F-measure. The logistic regression technique produced an accuracy of 76%. The comparative performance analysis of model for prediction of student’s performance has been performed with Naïve Bayes by using performance metrics, namely accuracy, specificity, sensitivity, and F-measure. It is observed that the 93% higher accuracy when compared with and 0.95 when compared.