Use an early warning system based on linked school and human services data to target resources and lessen risks before they become more serious¶

Strategy · All strategies
Evidence · no claims cited

Description¶

The article recommends that identifying the students most likely to have certain types of academic problems in the near term "can support an early warning system that allows educators and human services staff to better target resources and lessen risks before they become more serious." The strategy is to act on near-term risk predictions from linked data so interventions reach students early, with both school staff and human services staff acting on the same risk signals.

Design Implications¶

Context¶

Requirements¶

• A working approach for identifying students most likely to have near-term academic problems, built on linked school and human services data

Constraints¶

Target Learners¶

• K-12 students at risk of near-term academic problems

Target Learning Goals¶

• Preventing escalation of academic problems through early, targeted allocation of educator and human services resources

Related Strategies¶

• Combine in-school and out-of-school data sources to understand and support students flagged as at risk
• Build early-warning indicators and leverage online-learning-system process data to support students before gaps widen in Grade 3
• Use findings on strategy–time-management links to develop early warning systems and interventions promoting effective time management and strategy use in flipped classrooms
• Use school-level data systems to identify which students need which types of support for dropout prevention
• Use longitudinal student-level data systems to diagnose dropout scope and identify at-risk students before key transitions
• Use linked cross-system data to target programs such as dropout prevention and postsecondary preparation for students in foster care
• Implement a web of supports for students in foster care: one-stop resource centers, school-based liaisons, tiered services, and cross-system collaboration
• Use early cheating-risk predictions only for low-stakes support with human review, never for disciplinary decisions
• Use early-session timing signals, interpreted relative to proficiency, to identify students needing adaptive support
• Implement early-warning systems in real classrooms using easily accessible data and transparent machine learning techniques
• Use explainable machine learning early warning systems to help teachers identify struggling inquiry learners early
• Use dropout among siblings and same-age intimates as risk markers to target prevention resources and monitoring

Examples¶

-

Key Sources¶

• Julie Bruch, Jonathan Gellar, Lindsay Cattell, John Hotchkiss, and Phil Killewald. (2020). Using Data from Schools and Child Welfare Agencies to Predict Near-Term Academic Risks, Snapshot. Regional Educational Laboratory Mid-Atlantic. https://ies.ed.gov/ncee/edlabs