ML-based identification of students at risk of failing or late completion
Collect and ingest data about students that have passed, and those that have failed. This includes attendance, hours spent on tasks (self-reported and reported), time left in subject/course, difficulties, LMS interactions and more to ensure the on-time completion of courses.
Use direct feedback from tutor, lecturer, course assessment and other signals such as pass rates and LMS data to determine success.
Maximising completion rates results in greater university revenue.
ML-based personalisation
Create student profiles to provide personalised course materials (personalised learning), identify potential /new students, cross/up-sell to masters, PHD and other degrees based on learning progression and interests.
cs software to monitor PPE compliance and safety monitoring to ensure employee safety.
CE&E, Theme & Comment Analytics
Improve collection and understanding of topics, context, and survey results from social media sites such as Facebook, feedback and survey reviews from Google Reviews.