The use of predictive analytics to effectively identify patients who can benefit from medical interventions in an effort to improve outcomes is a growing movement. One common method for identifying these patients is through population segmentation, a process in which individuals are grouped into cohorts that share common characteristics and require similar interventions to help improve the quality of their care. This paper explores four common methods for population segmentation: cost cohort segmentation, condition cohort segmentation, utilization cohort segmentation, and social cohort segmentation.