prediction of smartphone addiction using ML

Smartphone addiction has emerged as a significant behavioral issue in the digital age, impacting mental health, productivity, and social interactions. This project leverages machine learning to predict smartphone addiction based on usage patterns and demographic data. Utilizing a Kaggle dataset with 13,589 records and 10 features (e.g., daily screen time, social media usage, notifications), we developed and evaluated nine machine learning models: Support Vector Machine, Decision Tree, Random Forest, AdaBoost, XGBoost, Stacking Classifier, Artificial Neural Network (ANN), Deep Neural Network (DNN), and Convolutional Neural Network (CNN). The Stacking Classifier and CNN achieved the highest testing accuracy of 98.38%. A Flask-based web application was developed to deploy the Stacking Classifier, enabling users to input features and receive real-time addiction predictions. Supported by a MySQL database for user management, the application provides an accessible interface for assessing smartphone addiction risk. This project demonstrates the efficacy of ensemble and neural network models in behavioral prediction and offers a practical tool for raising awareness about smartphone overuse.