AI-BASED PERSONALIZED LEARNING AND STUDENT PERFORMANCE PREDICTION SYSTEM

Abstract

Artificial Intelligence (AI) is becoming increasingly useful in the field of education. Different students have different learning abilities, strengths, and weaknesses, but traditional education systems often provide the same learning materials and support to all students. This can make it difficult for teachers to identify students who need additional academic support. This paper proposes an AI-driven personalized learning system for student performance prediction and early academic intervention. The proposed system uses student information such as marks, attendance, assignment scores, quiz scores, study hours, and learning activities to analyze academic performance. Machine learning techniques are used to predict future student performance and identify students who may be at risk of poor academic results. Based on the student's performance and weak areas, the system provides personalized learning recommendations such as study materials, practice questions, videos, and quizzes. The system also helps teachers monitor student progress and identify students who need additional support at an early stage. Different machine learning algorithms can be compared to determine a suitable model for student performance prediction. The proposed framework connects prediction, learning-gap identification, personalized recommendation, and early intervention in a single workflow. The approach can support data-driven educational decisions while keeping teachers involved in the final interpretation and intervention process.