Multi-Parameter Based Educational Recommendation System for Online Courses: A Content Based Filtering Approach

There are now an excessive number of courses available to students of all ages and skill levels as a result of the development of online education. Finding the courses that best meet their needs has become difficult for students as a result of this. In order to solve this problem, we describe an educational recommendation system (ERS) that uses cosine similarity (CS) and content-based filtering (CBF) to suggest online courses to users based on their search terms. This approach uses a dataset of online courses that includes information about several course parameters, including course title, enrolment figures, price, reviews, duration, and topic matter. In this paper, we begin with a comprehensive review of existing literature related to ERS. We then describe methodology and approaches to developing the system along with the process of dataset selection and pre-processing steps, feature extraction, and the evaluation metrics used to assess the system's performance. The system was able to identify and recommend courses that were highly relevant to the user's query, with a precision rate of over 90%.