Ouroboros: early identification of at-risk students without models based on legacy data
- Submitting institution
-
The Open University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1658551
- Type
- E - Conference contribution
- DOI
-
10.1145/3027385.3027449
- Title of conference / published proceedings
- LAK17 - Seventh International Learning Analytics & Knowledge Conference
- First page
- 6
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- March
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- 23 - Education
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
2
- Research group(s)
-
-
- Citation count
- 22
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper was accepted at the best conference in Learning Analytics (LAK'17 acceptance rate 32%). It presents a novel method for predicting student outcomes in a course without legacy data. The paper has led to subsequent framework generalising the problem to achieving any milestone (Hlosta et al., 2018). It enabled prediction on new courses in production at the OU for 3 years in 25 modules impacting 13,252 students before being superseded by a newer model. Learning Analytics researchers cite it when referring to methods capable of predicting without historical data (Helal et al., 2018; Hussain et al., 2019).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -