An AI Based Predictive Model for Personalized Learning Integrating Behavioral Cognitive and Adaptive Factors

This study examines the development and evaluation of an artificial intelligence (AI)-based model for personalized learning, designed to enhance student performance through behavioral and cognitive data analysis. Using a dataset of 500 observations, the research analyzed nine key variables, including hours_coding, cognitive_load, sleep_hours, and ai_usage_hours. Descriptive analysis showed that participants spent an average of 5.02 hours on learning activities per session, engaged with AI tools for 1.51 hours, and achieved an average task success rate of 60.6%. Correlation analysis revealed that hours_coding (r = 0.62) and coffee_intake_mg (r = 0.70) had the strongest positive relationships with task success, while sleep_hours and cognitive_load exhibited a strong negative correlation (r = –0.73). A Random Forest Classifier was applied to predict learning outcomes, achieving a perfect accuracy of 100%, with precision, recall, and F1-score values of 1.00 for both successful and unsuccessful learners. Feature importance analysis identified hours_coding (38.5%) and coffee_intake_mg (28.8%) as the most influential factors, followed by cognitive_load (14.5%) and ai_usage_hours (3.1%). These findings indicate that while AI contributes positively to personalized learning, behavioral and cognitive factors remain the primary determinants of success. The study concludes that AI serves best as a supportive tool that enhances learner autonomy and adaptability, emphasizing the need for a balanced integration of human engagement and intelligent technology in modern education.