Answers are grounded in this paper and cite their sources.
This study aims to identify factors that refine recommendations for reducing adolescent handgun carriage via machine learning. Data from 154,276 middle and high school students using the 2018, 2020, and 2022 Florida Youth Substance Abuse Survey was analyzed. The handgun carriage model achieved a Receiver Operator Characteristic Area Under the Curve (ROC AUC) score of 0.95, indicating 95% accuracy in distinguishing handgun carriers from non-carriers. The model achieved a Precision-Recall Area Under the Curve (PR AUC) score of 0.72, indicating both high precision (few false positives) and recall (few false negatives). The model predicting bringing a handgun to school performed well (ROC AUC = 0.97; PR AUC = 0.65). Approaches targeting youth substance use, increased parental monitoring, and secure firearm storage could reduce handgun carriage.
No takes yet. Share an insight, caveat, or question.
Trucco et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: