This paper reports on the research findings of the Open Academic Analytics Initiative, and features eight findings.
Most positive is the finding that relatively simple intervention strategies designed to alert students early in a course that they may be at risk academically can have a positive impact on student learning outcomes such as overall course grades.
Most concerning is the finding that interventions can have unintended consequences, such as triggering students to withdraw from courses to avoid academic and financial penalties.
- The feasibility of implementing an open‐source early‐alert prototype for higher education, and provides a detailed account of the challenges and design criteria used in implementing such a system.
- The strength of scores derived from partial contributions to the student’s final grade as predictors of academic performance.
- How these predictive models can help the instructor detect students at academic risk earlier in the semester.
- Initial evidence that predictive models can be imported from the academic context in which they were developed to different academic contexts while retaining most of their predictive power.
- That there may be benefits associated with customizing imported predictive models using local institutional data as a means to enhance their predictive power further.
- That there are no apparent gains between providing students with an online academic support environment and simply making students aware of their potential academic risk.