International Research Journal of Education and Technology

The Mobile Addiction Prediction System is a machine learning-based web application that analyzes user behavior patterns to predict smartphone addiction levels. With increasing mobile dependency affecting mental health, productivity, and social interactions, this system offers an automated, data-driven solution to promote digital well-being. Users can upload smartphone usage data, including screen time, app usage, and unlock frequency, via CSV files or real-time tracking. The system processes this data using AI models to classify addiction levels and provides personalized recommendations for healthier digital habits. Built with React.js for the frontend, Firebase for authentication and storage, and Flask for backend processing, the platform ensures secure, scalable, and efficient data management. The interactive web dashboard presents historical trends, graphical reports, and actionable insights, empowering users to monitor and reduce excessive mobile usage. By leveraging cloud-based machine learning models and privacy-focused infrastructure, the system ensures accurate predictions while safeguarding user data. This project serves as a valuable tool for individuals, parents, educators, and mental health professionals seeking to understand and manage smartphone dependency. Through real-time analytics and intuitive visualizations, the system enhances self-awareness and encourages responsible smartphone consumption.

Key Words:  Mobile Addiction Prediction, Machine Learning, Smartphone Usage Analysis, Digital Well-being, Predictive Analytics, Screen Time Monitoring, Behavioral Data Analysis, AI-Powered Insights.