Development Of Learning Path Recommendation System Using The Deep Learning Based O-Recurrent Learnernet

Abstract

Recent focus has been directed on programming education due to the rising need for programming and information technology competencies. Nonetheless, an insufficiency of instructional materials and personnel is a significant obstacle to fulfilling the increasing demand for programming education. One method to mitigate the deficit of qualified educators is to use deep learning approaches to support students. We present a learning route recommendation system using a student's ability chart via an optimised recurrent learner network. The learning route index dataset was first acquired via Kaggle. The data may thereafter be processed via the error splash quartz filter. The various course-related characteristics are grouped using the wrapper-k-doc technique. Finally, the path recommendation system was developed using the O-recurrent learner net algorithm. Here the classifier parameters are hypertuned using the greywolf optimizer algorithm. The overall experimentation was carried out in a Python environment. From the analysis, the suggested methodology overcomes the existing methodology by obtaining a high range of accuracy(99.9%).