Identifying students at risk of dropping out is no easy task. Each student has unique needs, and it can be a challenge to provide the right support, at the right time. Threshold dropout prevention models often use a “one-size-fits-all” approach, and begin to identify at-risk students late in their academic career, often after a student has become disengaged with school.
Next generation predictive analytic models measure risk factors based on each district’s actual data and historical graduation rates. This model creates a personalized risk profile for each student, within each district, and identifies at-risk students as early as first grade, with 94% accuracy.
Download our engaging infographic to discover the significance of predictive analytics, and view the vast diversity between risk indicators across grade levels.