AI for education: early detection of at-risk students
WYnova applies artificial intelligence in education to identify students at risk of dropping out in time to intervene, using the data the institution already records.
Contact WYnovaCommon challenges in the sector
Dropout identified when there is no longer any room to intervene.
Assessments, attendance and participation recorded in systems that do not communicate with each other.
Teachers and school leadership without an up-to-date list of the students who need support.
Early detection of students at risk of dropping out
Challenge
Identify students at risk of dropping out while there is still time to intervene, without adding administrative work for teachers.
Proposed approach
A machine learning model combines performance, attendance and participation data, assigns a risk level to each student and proposes interventions. Teachers review and validate the alerts in a dashboard, with role-based access to student data.
Expected result
Teachers now have a prioritised list of at-risk students and intervene earlier, with each alert justified by the data that triggered it.
Technical areas: ML, Data Eng, BI
Other sectors
Health
Assisted clinical documentation, with medical validation.
Media
A video and audio archive that can be searched by meaning.
Public sector
Analysis of bids in public tenders, with cited sources.