The extensive research under way to forecast traffic volumes from real-time data is expected to result in a significant increase in the use of real-time data for congestion mitigation and management in the next few years. Unfortunately, congestion-mitigation strategies based solely on these forecast volumes will disregard the impact of other traffic variables on crash occurrence. This may result in congestion-mitigation strategies that improve traffic flow but significantly increase crash rates. These other variables, for which real-time data are also available in traffic management centers, include speed and occupancy. However, real-time data have not been widely used in research to develop mathematical models that relate crash rates with these other traffic variables. The availability of this type of relationship will enable engineers in the field to develop congestion-mitigation strategies based not only on forecast volumes but also on real-time information on traffic variables such as speed and occupancy. A procedure that uses real-time data on traffic flow, speed, and occupancy and the relationship between these variables and crash occurrence could be used to develop congestion-mitigation strategies that incorporate safety. Currently, no such decision-support tool is readily available to the traffic engineer. The feasibility of developing such a methodology in which real-time data could be used to develop congestion-mitigation strategies that also consider crash risk was investigated. Models showing the relationship between flow and occupancy and between number of crashes and occupancy were developed for specific sites in the Hampton Roads, Virginia, area. These models were then used to illustrate how diversion strategies that consider crash risk may be developed.