Recommender Systems and Machine Learning Techniques for Large Educational Data: A Survey

Recommendation systems are widely used in domains such as e-commerce, social media networks, news portals, educational platforms, and other related fields. This survey presents an overview of state-of-the art recommender systems and machine learning techniques applied to analyze data. Different ML algorithms have been utilized in building these systems, including Naive Bayes (NB), Support Vector Machines (SVM), K Nearest Neighbor (KNN), Decision Tree (DT), and others. Many of these algorithms have shown accuracy and broad adoption by employing learning methods to support educational practices and provide recommendations in the field of education. The core methodologies employed in recommender systems consist of a content-based approach, a collaborative approach, and a hybrid approach. The findings of this study indicate a growth in research on recommender systems in recent years. The paper offers an analysis of the approaches and trends utilized in recommender systems for data.