Machine learning based recommender system for improving student's learning experience

In the contemporary educational landscape, personalized learning experiences are increasingly valued for their potential to enhance student engagement and performance. This project introduces a machine learning-based recommender system tailored specifically for improving students' learning journeys. The system utilizes a dataset comprising various attributes including student IDs, assignment scores, gender, course information, and ratings.The methodology involves several key steps. Initially, the dataset undergoes preprocessing, where features such as average scores and total attempts across multiple assignments are calculated and redundant columns are eliminated. Subsequently, text data associated with courses is vectorized using Term Frequency-Inverse Document Frequency (TF-IDF) representation, enabling the system to understand course descriptions effectively. Moreover, numerical features like gender, rating, average scores, and total attempts are standardized to ensure consistency and comparability.The recommendation engine employs the K-Nearest Neighbors (KNN) algorithm to identify courses most relevant to a given student's profile. By combining both numerical and textual features, the system can generate personalized recommendations based on similarities between students' attributes and course descriptions. This hybrid approach enhances the accuracy and relevance of recommendations, fostering a more tailored learning experience for each student.The web application interface built using Flask facilitates user interaction with the recommender system. Students can input their gender, average scores, number of attempts, and rating preferences to receive personalized course recommendations. Upon submission, the system computes the nearest neighbors based on the provided features and presents the recommended courses to the user.Overall, this project represents a significant advancement in leveraging machine learning techniques to enhance students' learning experiences. By offering personalized course recommendations tailored to individual profiles, the system contributes to fostering a more engaging, effective, and fulfilling educational journey for students across diverse academic domains.

 Keywords: Recommender system, Education, KNN, Course Recommendations, Personalized Learning.