Enhancing Military Personnel Safety, Minimizing Negative Actions, and Enhancing Battle Preparedness Through Data Usage
In a bid to proactively address harmful behaviors within the military, a groundbreaking initiative has been launched on Fort Carson, Colorado. Known as the Unit Risk Forecasting Tool (URFT), this innovative project was developed by a data analytics and innovation team within the 4th Infantry Division.
The URFT, initially designed to identify units at risk of harmful behaviors, has undergone significant enhancements over the past year and a half. It now employs more sophisticated data models such as logistic regression, Poisson regression, and XGBoost to find hidden connections in the data and improve predictions.
The tool now incorporates a broader range of data sources, extending from Fort Carson to additional Army installations. It takes into account company-level variables like the total number of officers, the number of noncommissioned officers, the number of junior enlisted personnel, average Army Combat Fitness Test scores, the percentage of soldiers medically ready for deployment, and the primary function of each unit (simplified to combat, support, or headquarters).
One of the key findings from the URFT is that effective supervision is a protective factor in reducing harmful behaviors. As the ratio of noncommissioned officers to junior enlisted soldiers increases, the predicted number of harmful incidents significantly decreases. Contrarily, a large population of junior soldiers, in itself, is not a predictor of high risk, so long as there is a correspondingly strong cadre of noncommissioned officers to lead them.
The URFT has already shown promising results. During a division-level pilot program in 2024, it managed to reduce serious incident reports (SIRs) across the participating brigade by 10 to 20 percent over the course of the year.
The ultimate goal is to deploy these predictive models on a secure, user-friendly digital platform that can provide automated alerts to leaders Army-wide. This would enable commanders to strategically allocate their time and attention to address underlying issues before they escalate into harmful behaviors.
To make the URFT more forward-looking, data from the Army Vantage Data Analytics Platform was pulled to create a richer, more holistic snapshot of each unit. This has allowed the tool to identify a phenomenon called the momentum effect, where units that had experienced a recent surge in harmful events were significantly more likely to see additional harmful events in the near future.
The URFT applies predictive data analytics to help leaders identify units at increased risk of harmful behaviors and take timely, preventive interventions. Its methodology could potentially be adapted to predict combat-related events, logistical shortfalls, or maintenance issues.
However, the challenges include robust data architecture and continuous collaboration with data owners across the entire institution to ensure a steady flow of high-quality information. Despite these challenges, the URFT represents a significant step forward in proactive risk management within the military.
In addition, the URFT provides actionable intelligence to leaders, allowing them to proactively engage with units flagged by the URFT. This approach not only aims to reduce harmful behaviors but also fosters a culture of prevention and proactive intervention within the military.
