Because of the high costs and burden of injuries, even small reductions in injury rates can be extremely valuable. Knowledge of which individuals in a group are most at risk can enable targeted injury rate reduction efforts. Though we can’t predict specific injury events without supernatural foresight—who will be injured and when— for a given population of people and period of time, some people are predictably more likely to be injured than others. Rapidly expanding capabilities, availability of data collection, and machine learning technologies are making operational injury risk assessment a reality. This brief white paper explains the basic foundation and requirements for a data-driven approach to relative injury risk assessment.