Difference between revisions of "Public or Private K-12 School"

From Penn Center for Learning Analytics Wiki
Jump to navigation Jump to search
Line 3: Line 3:
* Several algorithms achieved better AUC and F1 for students who attended public high schools than for students who attended private high schools.
* Several algorithms achieved better AUC and F1 for students who attended public high schools than for students who attended private high schools.


Queiroga et al. (2022) [https://doi.org/10.3390/info13090401 pdf]


Queiroga et al. (2022) <nowiki>[https://doi.org/10.3390/info13090401 pdf]</nowiki>
* Models predicting secondary school students at risk of failure or dropping out.
 
* Models achieved high performances with an AUROC higher than 0.90 and F1-Macro higher than 0.88.
<nowiki>*</nowiki> Models predicting secondary school students at risk of failure or dropping out.
* Models achieve better results when new data comes from the secondary education period (e.g., model M2G1-UTU achieved a performance of 95%).
 
* First-year primary school zones (rural or urban) and sixth-year assessment-based grouping are two of the most important attributes of this model.
<nowiki>*</nowiki> Models achieved high performances with an AUROC higher than 0.90 and F1-Macro higher than 0.88.
 
<nowiki>*</nowiki> Models achieve better results when new data comes from the secondary education period (e.g., model M2G1-UTU achieved a performance of 95%).
 
<nowiki>*</nowiki> First-year primary school zones (rural or urban) and sixth-year assessment-based grouping are two of the most important attributes of this model.

Revision as of 16:08, 29 May 2023

Verdugo et al. (2022) pdf

  • An algorithm predicting dropout from university after the first year
  • Several algorithms achieved better AUC and F1 for students who attended public high schools than for students who attended private high schools.

Queiroga et al. (2022) pdf

  • Models predicting secondary school students at risk of failure or dropping out.
  • Models achieved high performances with an AUROC higher than 0.90 and F1-Macro higher than 0.88.
  • Models achieve better results when new data comes from the secondary education period (e.g., model M2G1-UTU achieved a performance of 95%).
  • First-year primary school zones (rural or urban) and sixth-year assessment-based grouping are two of the most important attributes of this model.