Machine learning model for prediction of smartphone addiction

Smartphone addiction has emerged a critical issue affecting adolescents and young adults, often resulting in academic decline, psychological stress, and reduced well- being. Excessive engagement in activities such as social media, gaming, and prolonged screen exposure contributes significantly to this problem. Machine learning methods such as Random Forest, Logistic Regression, and Support Vector Machines (SVM) to predict smartphone addiction based on quantifiable features like daily screen usage, social media activity, gaming time, and the count of installed apps. An interactive dashboard built with Streamlit and Altair is integrated to visualize results and provide real-time feedback. Furthermore, recent advances in behavioral analytics, explainable AI, and digital wellness technologies highlight the growing potential for intelligent systems to enable early detection and intervention. The proposed framework contributes to supporting healthier smartphone use by combining predictive modeling with interpretable visualization tools.