Abstract
This chapter discusses the literature and practice on emerging technologies to predict and prevent dropping out of upper secondary school. First, it presents the current research on early warning systems and early warning indicators and discusses the accuracy of predictors of dropout. It shows the value of such research, including a typology of dropout profiles. Second, it provides an overview of current emerging digital methodologies from pattern analytics, data science, big data analytics, learning analytics, and machine learning as applied to identifying accurate predictors of dropping out. The conclusion looks to the future of early warning systems and indicators, both from a research and policy perspective, calling for the need for open access algorithms and code for early warning systems and indicators research and practice, and for the inclusion of the community in their design and application, proposing a framework of “Four A’s of Early Warning Indicators” so that they are Accurate, Accessible, Actionable and Accountable.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call