Empower artificial intelligence webinar week a personalized early warning system for supporting learners the uoc case by david baneres

1. A personalized early warning system for supporting learners: the UOC case David Bañeres (dbaneres@uoc.edu) Universitat Oberta de Catalunya

2. UOC Virtual Campus StaffFaculty Students

3. UOC Virtual Campus StaffFaculty Students - Provide support - Manage programmes - Manage system - Solve questions - Provide support - Prepare activities - Assess activities - Generate resources - …- …

4. • Some repetitive tasks can be (semi)-automated Potential enhancement: • We can provide a real 24x7 support to students • We can provide a better personalized support

5. LIS: Learning Intelligent System • Project supported by the eLearn Center through the New Goals call • 3 years project • A research group composed of 4 members

6. Principal Aim To develop an adaptive system to be globally applicable at UOC campus to help students to succeed in their learning process.

7. Predictive Analytics Early Warning System Automated Recommendations Automated feedback My Checklist Gamified Interface Research topics

8. Predictive Analytics Early Warning System Automated Recommendations Automated feedback My Checklist Gamified Interface Research topics

9. Outline • GAR predictive model • Infrastructure • Dashboards • Nudgeting system

11. CAA1 CAA2 … CAAn ? Pass Course? Grade CAA1 Grade CAA1, Grade CAA2 Grade CAA1, Grade CAA2,…, Grade CAAn Students at-risk identification model v1

12. CAA1 CAA2 … CAAn ? Pass Course? Accuracy Detect At-risk 56% 87% 91% Acc. Detect Non-at-risk 93% 95% 97% Students at-risk identification model v1

13. CAA1 CAA2 … CAAn ? Pass Course? Grades CAANewbie Student Enrolled Courses Semester Failed Times Course GPA Profile Student + Students at-risk identification model v2

14. 56% 87% 91% 93% 95% 97% CAA1 CAA2 … CAAn ? Pass Course? Accuracy Detect At-risk 81% 88% 92% Acc. Detect Non-at-risk 92% 92% 96% Profile Student Students at-risk identification model v2

15. Accuracy Threshold High quality Low quality Relevancy of accuracy on real setting

16. Model for a CAA Accuracy Threshold High quality Low quality Relevancy of accuracy on real setting

17. Model for a CAA Accuracy Threshold High quality Low quality Relevancy of accuracy on real setting

18. Relevancy of accuracy on real setting Model for a CAA 75% High quality Low quality Accuracy Threshold

20. Infrastructure

21. Infrastructure Institutional data mart

22. Infrastructure Computational service

23. Infrastructure Informational service

24. Infrastructure Desanonamyzer service

25. Infrastructure Nudgeting service

27. Grade CAA1 Grade CAA2 Pass? B A PASS B B PASS B C+ FAIL B C- FAIL B D FAIL B N FAIL CAA2 Student’s dashboard v1 Fail Pass

28. Student’s dashboard v2

29. Grade CAA1 Grade CAA2 Pass? B A PASS B B PASS B C+ FAIL B C- FAIL B D FAIL B N FAIL CAA2 Student’s dashboard v2

30. Teacher dashboards

31. Teacher dashboards

32. Teacher dashboards Recovered Students

34. Consecutive non-submitted One activity non-submitted Likelihood to fail May fail but low accuracy model May pass but low accuracy model Likelihood to passPass the activity but grade lower than prediction Prediction feedback Nudgeting system

35. Consecutive non-submitted One activity non-submitted Submit activity Informational feedback Nudgeting system

36. Not accessed on activity Not yet submitted activity Already submitted the activity Remainder Nudgeting system

37. Lessons learned ● Predictive model needs further analysis to be applied on real setting ● Infrastructure solves particular UOC setting ● Is the EWS/nudgeting system really useful?

38. UOCresearch @UOC_research http://lis-project.research.uoc.edu/ Welcome LIS at UOC, we expect that you succeed as students do.