Personalized E-Learning Recommendation System Using K-Nearest Neighbor Algorithm

In recent years, the expansion of e-learning platforms has revolutionized the educational landscape, offering learners the flexibility to access educational resources anytime and anywhere. However, the abundance of content often overwhelms students, making it difficult to identify which learning materials best suit their individual needs. To address this challenge, this study proposes the development of a Personalized E-Learning Recommendation System that utilizes the K-Nearest Neighbor (KNN) algorithm to tailor learning content based on each learner’s profile, behavior, and preferences. The primary objective of this research is to design and implement a data-driven recommendation model that enhances learner engagement and academic performance by providing customized content suggestions. The system collects various types of user data from the e-learning platform, including quiz scores, subject interests, time spent on modules, and interaction history. Each learner is represented as a feature vector encapsulating these attributes. By applying the KNN algorithm, the system identifies students with similar learning patterns and preferences and recommends educational resources that have proven effective for those peers. The study follows a design and development research methodology, where the system is built, tested, and evaluated through iterative processes. The prototype is developed using Python and its machine learning libraries, while a web-based interface is created using Django and integrated with a backend database to store user data. Evaluation metrics such as recommendation accuracy, user engagement rate, and improvement in quiz performance are used to assess the system’s effectiveness. Initial testing shows that learners receiving personalized recommendations spend more time on the platform and demonstrate higher content retention compared to those accessing randomly assigned materials. This research contributes to the growing field of intelligent e-learning systems by highlighting the effectiveness of simple yet powerful machine learning techniques such as KNN in improving personalization. It also emphasizes the value of learner data in shaping adaptive educational environments that cater to individual learning styles and needs. Future work may include expanding the dataset, incorporating hybrid recommendation models, and exploring deep learning approaches to further improve recommendation quality. By offering a scalable and adaptable framework, this personalized recommendation system has the potential to significantly enhance the digital learning experience, making online education more targeted, efficient, and impactful.