Predicting Drug Addiction in Students using Artificial Intelligence: A Machine Learning Approach

Abstract

This paper presents a novel approach leveraging artificial intelligence (AI) and machine learning (ML) techniques to predict drug addiction among students. The proposed methodology involves the collection of comprehensive data encompassing various factors such as demographics, socio-economic status, academic performance, family history of addiction, peer influence, mental health status, and substance use history. Following data preprocessing and feature selection, different ML algorithms including logistic regression, decision trees, random forests, support vector machines (SVM), and neural networks are trained and evaluated to identify the most effective model for prediction. The developed model is deployed into a user-friendly interface, enabling early intervention and prevention efforts to mitigate the risks associated with substance abuse among students. Ethical considerations regarding data privacy, fairness, and transparency are also addressed throughout the study. Experimental results demonstrate the efficacy of the proposed approach in predicting drug addiction in students, thereby contributing to proactive interventions for promoting student well-being and health.