COURSE RECOMMENDATION ENGINE USING MACHINE LEARNING

Abstract

            In the rapidly evolving landscape of education and educational field, efficient categorization of courses is imperative for enhancing user experience, utilizing personal interests, and providing personalized recommendations. This study explores the application of machine learning techniques for automating the prediction of educational courses based on personal interests. Leveraging a diverse and labelled dataset, we employ state-of-the-art natural language processing and machine learning algorithms to extract meaningful features from userpersonal interests and make accurate course predictions. The process encompasses data collection, pre-processing, and feature extraction, etc are utilized to capture intricate semantic relationships within user personal interests. Model selection involves the careful consideration of algorithms such as naive bayes, random forest, or linear SVM, tailored to the specifics of courser commendation. Training and evaluation on labelled datasets facilitate the optimization of model parameters, ensuring robust performance on unseen data. The deployed model is seamlessly integrated into a carer platform, providing predictions including upcoming courses. Continuous monitoring and maintenance mechanisms are implemented to adapt to evolving product catalogues and changing linguistic patterns. The study also addresses challenges related to imbalanced datasets and explores ensemble methods to improve predictive accuracy. The proposed approach not only streamlines the product categorization process but also lays the foundation for adaptive systems capable of accommodating new categories and contextual information. The findings of this research contribute to the advancement of machine learning applications in the course recommendation, offering a scalable and efficient solution for selecting an appropriate course in dynamic online platforms.

Author

Dr.S. Kayalvili , Bhuvanesh.M , Mohamed Ajmal.S , Kaarthi.G