Deep learning enabled course recommendation platform

Abstract

E-learning platforms have gained much recognition in the field of teaching and learning, especially after the outbreak of Covid 19. Many aids have been produced considering the demand for the online platform. One such aid is Learning Management System (LMS). However, the prediction performance of the learner is challenging in LMS. Enabling a student to select a course, the function of the Course Recommendation system is vital. In order to rectify the deficiencies in the existing system, an intelligent system is recommended as it helps select a personalized set of data from a mass volume of information. The adjectives of this research are deep learning is considered for increasing the accuracy, the performance should be boosted with the proposed hybrid optimization technique, effectively perform the learning style prediction using the random forest for achieving a more accurate recommendation of the course, to analyze the performance of the developed Taylor-CSO algorithm for ensuring accuracy True Positive Rate (TPR) and True Negative Rate (TNR). Thus this research is an attempt to propose feasible methodologies for learning style-based performance prediction and course recommendation in the E-Khool learning platform using deep learning algorithms. This research will fill in the existing research gaps in the field of deep learning algorithms in electronic platforms.