Wisconsin Dropout Early Warning System

Released: 2012 

Can you improve this page?
Share your insights with us

Wisconsin's Dropout Early Warning System (DEWS) is a machine learning-based application that uses test scores, disciplinary records, family income, race and other factors to predict the likelihood of middle school students dropping out of high school on time. The system categorises students as a high, moderate or low risk of dropping out in order to help schools direct resources and support as necessary.

A 2023 Markup/ChalkBeat investigation discovered the system is wrong 'almost three-quarters of the time' that it predicts a student will not graduate, and wrong more often about Black and Hispanic students not graduating than it is about white students. It also found educators had not been properly trained to understand the dropout risk labels and intervene accordingly, and that students had not been informed about the existence of the system.

Meantime, University of California-Berkeley researchers found the system failed to achieve its primary goal of improving graduation outcomes for the students it labels as 'high risk'. They recommended Wisconsin scrap its use of individual factors such as a student’s race or even test scores in determining that student’s dropout risk.

The Wisconsin Department of Public Instruction told The Markup it is studying its early warning systems and considering making changes to DEWS.

Operator: Wisconsin Department of Public Instruction
Developer: Wisconsin Department of Public Instruction

Country: USA

Sector: Education

Purpose: Predict student drop-outs

Technology: Machine learning
Issue: Accuracy/reliability; Bias/discrimination - race, ethnicity

Transparency: Governance; Marketing