A Comparative Study of Machine Learning Algorithms for Drug Addiction Prediction

Abstract

Drug addiction is a pressing societal issue with far-reaching consequences. Accurate prediction of individuals at risk of drug addiction can greatly aid in prevention and intervention efforts. This study presents a comprehensive comparative analysis of three prominent machine learning algorithms: Classification and Regression Trees (CART), Support Vector Machines (SVM), and Random Forest, for the purpose of drug addiction prediction. The dataset used in this analysis contains a diverse set of attributes, including demographic information, mental and emotional health indicators, family dynamics, and prior experiences with drugs, making it a valuable resource for studying this complex issue. This study investigates the performance of these algorithms in predicting drug addiction based on the provided attributes, considering the factor accuracy. The results of this comparative analysis will contribute to the development of more accurate and efficient tools for identifying individuals at risk of drug addiction, ultimately assisting in the formulation of targeted prevention and intervention strategies.