At-risk/Dropout/Stopout/Graduation Prediction - Revision history

Shruti at 03:54, 28 November 2023

2023-11-28T03:54:18Z

← Older revision		Revision as of 23:54, 27 November 2023
Line 76:		Line 76:
	*Prediction is more accurate for low-income students than for non-low-income students		*Prediction is more accurate for low-income students than for non-low-income students
	*Prediction is comparable for Males and Females		*Prediction is comparable for Males and Females


	Cock et al.(2023) [[https://dl.acm.org/doi/abs/10.1145/3576050.3576149?casa_token=6Fjh-EUzN-gAAAAA%3AtpRMYzSAVoQFYNzwY5gwSsrnzHIlI0tUjMq6okwgdcCUmuBMVZEtn8eLO52dCtIYUbrHBV_Il9Sx pdf]]		Cock et al.(2023) [[https://dl.acm.org/doi/abs/10.1145/3576050.3576149?casa_token=6Fjh-EUzN-gAAAAA%3AtpRMYzSAVoQFYNzwY5gwSsrnzHIlI0tUjMq6okwgdcCUmuBMVZEtn8eLO52dCtIYUbrHBV_Il9Sx pdf]]

Shruti at 03:53, 28 November 2023

2023-11-28T03:53:47Z

← Older revision		Revision as of 23:53, 27 November 2023
Line 74:		Line 74:
	*Prediction is less accurate for White students than other students		*Prediction is less accurate for White students than other students
	*Prediction is more accurate for students with Disabilities than students without Disabilities		*Prediction is more accurate for students with Disabilities than students without Disabilities
	*Prediction is more accurate for low-income students than for non-low-income students.		*Prediction is more accurate for low-income students than for non-low-income students
	*Prediction is comparable for Males and Females		*Prediction is comparable for Males and Females

			Cock et al.(2023) [[https://dl.acm.org/doi/abs/10.1145/3576050.3576149?casa_token=6Fjh-EUzN-gAAAAA%3AtpRMYzSAVoQFYNzwY5gwSsrnzHIlI0tUjMq6okwgdcCUmuBMVZEtn8eLO52dCtIYUbrHBV_Il9Sx pdf]]
			* Paper investigates biases in models designed to early identify middle school students at risk of failing in flipped-classroom course and open-ended exploration environment (TugLet)
			* Model performs worse for students from school with higher socio-economic status in open-ended environment (FNR 0.73 for higher SES and 0.57 for medium SES).
			* Model performs worse for males in open-ended environment (higher FNR for males than females)
			* Model performs worse for students with diploma from foreign country in flipped classroom
			* Model performs worse for females in flipped classrooms

Ryan at 17:34, 29 June 2023

2023-06-29T17:34:21Z

← Older revision		Revision as of 13:34, 29 June 2023
Line 75:		Line 75:
	*Prediction is more accurate for students with Disabilities than students without Disabilities		*Prediction is more accurate for students with Disabilities than students without Disabilities
	*Prediction is more accurate for low-income students than for non-low-income students.		*Prediction is more accurate for low-income students than for non-low-income students.
	*~~DEWS prediction~~ is comparable for Males and Females		*Prediction is comparable for Males and Females

Shruti at 01:17, 29 June 2023

2023-06-29T01:17:31Z

Shruti at 01:16, 29 June 2023

2023-06-29T01:16:36Z

@@ Line 1: / Line 1: @@
 Kai et al. (2017) [https://www.upenn.edu/learninganalytics/ryanbaker/DLRN-eVersity.pdf pdf]
 * Models predicting student retention in an online college program
@@ Line 72: / Line 66: @@
 * Model was unable to make prediction of student success (F1 score = 0.0) for students not in a social welfare program (higher socioeconomic status)
 * Model had slightly lower AUC ROC (0.52 instead of 0.56) for students not in a social welfare program (higher socioeconomic status)

Shruti at 22:58, 28 June 2023

2023-06-28T22:58:23Z

← Older revision		Revision as of 18:58, 28 June 2023
Line 1:		Line 1:
	Permodo et al.(2023) [http://pdf ~~https~~://arxiv.org/abs/2304.06205]		Permodo et al.(2023) [http://pdf%20https://arxiv.org/abs/2304.06205 pdf]
	* Paper discusses system that predicts probabilities of on-time graduation		* Paper discusses system that predicts probabilities of on-time graduation
	*Prediction is less accurate for White students than other students		*Prediction is less accurate for White students than other students

Shruti: Addition

2023-06-28T22:57:33Z

Addition

← Older revision		Revision as of 18:57, 28 June 2023
Line 1:		Line 1:
			Permodo et al.(2023) [http://pdf https://arxiv.org/abs/2304.06205]
			* Paper discusses system that predicts probabilities of on-time graduation
			*Prediction is less accurate for White students than other students
			*Prediction is more accurate for students with Disabilities than students without Disabilities
			*Prediction is more accurate for low-income students than for non-low-income students.
			*DEWS prediction is comparable for Males and Females
	Kai et al. (2017) [https://www.upenn.edu/learninganalytics/ryanbaker/DLRN-eVersity.pdf pdf]		Kai et al. (2017) [https://www.upenn.edu/learninganalytics/ryanbaker/DLRN-eVersity.pdf pdf]
	* Models predicting student retention in an online college program		* Models predicting student retention in an online college program

Ryan: Rewrote Queiroga

2023-06-04T15:37:35Z

Rewrote Queiroga

← Older revision		Revision as of 11:37, 4 June 2023
Line 61:		Line 61:
	* Regardless of over-sampling method used, dropout performance was slightly better for males.		* Regardless of over-sampling method used, dropout performance was slightly better for males.

	Queiroga et al. (2022) [https://~~doi~~.~~org~~/~~10.3390~~/~~info13090401~~ pdf]		Queiroga et al. (2022) [https://www.mdpi.com/2078-2489/13/9/401 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 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%).~~		* Model was unable to make prediction of student success (F1 score = 0.0) for students not in a social welfare program (higher socioeconomic status)
	* First-year primary school zones (~~rural or urban~~) ~~and sixth year assessment-based grouping are two of the most important attributes of this model.~~		* Model had slightly lower AUC ROC (0.52 instead of 0.56) for students not in a social welfare program (higher socioeconomic status)

Zhanlan at 20:03, 29 May 2023

2023-05-29T20:03:10Z

← Older revision		Revision as of 16:03, 29 May 2023
Line 60:		Line 60:
	* A range of over-sampling methods tested		* A range of over-sampling methods tested
	* Regardless of over-sampling method used, dropout performance was slightly better for males.		* Regardless of over-sampling method used, dropout performance was slightly better for males.

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

Seiyon at 23:52, 21 December 2022

2022-12-21T23:52:12Z

← Older revision		Revision as of 19:52, 21 December 2022
Line 5:		Line 5:
	* JRip decision rules achieved almost identical Kappa and AUC for Black students and White students		* JRip decision rules achieved almost identical Kappa and AUC for Black students and White students
	* JRip decision trees achieved much lower Kappa and AUC for male students than female students		* JRip decision trees achieved much lower Kappa and AUC for male students than female students

			Hu and Rangwala (2020) [https://files.eric.ed.gov/fulltext/ED608050.pdf pdf]
			* Models predicting if a college student will fail in a course
			* Multiple cooperative classifier model (MCCM) model was the best at reducing bias, or discrimination against African-American students, while other models (particularly Logistic Regression and Rawlsian Fairness) performed far worse
			* The level of bias was inconsistent across courses, with MCCM prediction showing the least bias for Psychology and the greatest bias for Computer Science
			* Multiple cooperative classifier model (MCCM) model was the best at reducing bias, or discrimination against male students, performing particularly better for Psychology course.
			* Other models (Logistic Regression and Rawlsian Fairness) performed far worse for male students, performing particularly worse in Computer Science and Electrical Engineering.

← Older revision		Revision as of 21:17, 28 June 2023
Line 5:		Line 5:
	* JRip decision rules achieved almost identical Kappa and AUC for Black students and White students		* JRip decision rules achieved almost identical Kappa and AUC for Black students and White students
	* JRip decision trees achieved much lower Kappa and AUC for male students than female students		* JRip decision trees achieved much lower Kappa and AUC for male students than female students


	Hu and Rangwala (2020) [https://files.eric.ed.gov/fulltext/ED608050.pdf pdf]		Hu and Rangwala (2020) [https://files.eric.ed.gov/fulltext/ED608050.pdf pdf]
Line 12:		Line 13:
	* Multiple cooperative classifier model (MCCM) model was the best at reducing bias, or discrimination against male students, performing particularly better for Psychology course.		* Multiple cooperative classifier model (MCCM) model was the best at reducing bias, or discrimination against male students, performing particularly better for Psychology course.
	* Other models (Logistic Regression and Rawlsian Fairness) performed far worse for male students, performing particularly worse in Computer Science and Electrical Engineering.		* Other models (Logistic Regression and Rawlsian Fairness) performed far worse for male students, performing particularly worse in Computer Science and Electrical Engineering.



Line 50:		Line 50:
	* Whether the socio-demographic information was included or not, the model showed worse accuracy and true negative rates for residential students who are under-represented minority (URM; not White or Asian), male, first-generation, or with greater financial needs		* Whether the socio-demographic information was included or not, the model showed worse accuracy and true negative rates for residential students who are under-represented minority (URM; not White or Asian), male, first-generation, or with greater financial needs
	* Both accuracy and true negative rates were better for students who are first-generation, or with greater financial needs		* Both accuracy and true negative rates were better for students who are first-generation, or with greater financial needs


	Verdugo et al. (2022) [https://dl.acm.org/doi/abs/10.1145/3506860.3506902 pdf]		Verdugo et al. (2022) [https://dl.acm.org/doi/abs/10.1145/3506860.3506902 pdf]
Line 55:		Line 56:
	* 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.
	* Several algorithms predicted better AUC for male students than female students; F1 scores were more balanced.		* Several algorithms predicted better AUC for male students than female students; F1 scores were more balanced.


	Sha et al. (2022) [https://ieeexplore.ieee.org/abstract/document/9849852]		Sha et al. (2022) [https://ieeexplore.ieee.org/abstract/document/9849852]
Line 60:		Line 62:
	* A range of over-sampling methods tested		* A range of over-sampling methods tested
	* Regardless of over-sampling method used, dropout performance was slightly better for males.		* Regardless of over-sampling method used, dropout performance was slightly better for males.


	Queiroga et al. (2022) [https://www.mdpi.com/2078-2489/13/9/401 pdf]		Queiroga et al. (2022) [https://www.mdpi.com/2078-2489/13/9/401 pdf]

	* Models predicting secondary school students at risk of failure or dropping out		* Models predicting secondary school students at risk of failure or dropping out
	* Model was unable to make prediction of student success (F1 score = 0.0) for students not in a social welfare program (higher socioeconomic status)		* Model was unable to make prediction of student success (F1 score = 0.0) for students not in a social welfare program (higher socioeconomic status)