The widespread problem of drug addiction remains a major public health issue in Bangladesh, demanding a thorough exploration of its root causes and predictive models. Data was gathered from 1104 individuals' survey responses, covering diverse demographic and behavioral characteristics. To evaluate their predictive potential, the data was examined using machine learning methods such as Decision Tree, Logistic Regression, K-Nearest Neighbor (KNN) Classifier, Naïve Bayes Classifier, and XGBoost Classifier. Our results demonstrate that the machine learning models serve as effective tools for comprehending and forecasting drug addiction within the Bangladeshi context. The performance metrics for each algorithm are as follows: Decision Tree (98% accuracy), KNN (98% accuracy), Logistic Regression (92% accuracy), Naïve Bayes (88% accuracy), and XGBoost (98%). These models exhibit promising capabilities, with Decision Tree, KNN, and XGBoost notably achieving a 98% accuracy rate in predicting drug addiction. These findings establish a solid foundation for future investigations into the complexities of drug addiction and the creation of more sophisticated predictive models specifically tailored to the context of Bangladesh.