Analysis of changing behavioral patterns in student parent domain using Reinforcement Learning and Machine Learning methods to predict Psychological Disorders

This study takes a critical look at the opportunities and difficulties faced by students in higher education who are moving from adolescence to young adulthood (18 to 25 years old). It integrates interdisciplinary viewpoints from psychology, education, and public health to comprehend and promote students’ behavioral well-being. The identification of behavioral patterns, risk factors for scholastic challenges, mental health issues, and novel approaches such as machine learning for early intervention are among the main subjects. K-means, KNN, Clustering, Reinforcement learning, Actor-Critic Method, Multi Linear Regression, and Q-Learning are among the algorithms used.