Application of Clustering Algorithms to enhance Personalized Learning through Recommendation Model

Technology and education have recently changed student involvement with learning resources and educational experiences. It is very important to have a platform which can provide personalized learning resources and group students by learning patterns. The research develops recommendation systems and grouping algorithms to help students with their learning patterns and performance measures. To record multidimensional student learning experiences, demographics, learning activities, problem-solving behaviours, and performance measures are extracted and processed. This system makes personalised student suggestions via collaborative filtering, especially Alternating Least Squares (ALS). The model predicts learning materials and problem sets based on student preferences and ability levels by analysing historical student interactions with learning resources. The research also uses clustering methods like K-means clustering to group students with similar learning and performance patterns. Clustering analysis lets instructors discover student group traits and tailor interventions and support techniques. This research also examines temporal relationships in student learning sequences using sequential models. Sequential learning activities and problem-solving behaviour of students help recurrent neural networks (RNNs), or sequential pattern mining algorithms predict their next activities. This research used a huge dataset of over sixteen million exercise logs and applied collaborative filtering (ALS) and K-means clustering to find learning patterns. The ALS-based recommendation system achieved a Mean Squared Error (MSE) of 0.23, showed excellent predictive accuracy. Clustering grouped students by learning behaviours, enabling targeted interventions. This research improves personalised learning using machine learning and data analytics in education. The recommendation system can help instructors tailor training, give individualised support, and boost academic success for various pupils by revealing student learning patterns.