Course Grade and GPA Prediction - Revision history

Valdemar: Add Svabensky@EDM'24

2024-09-02T00:06:09Z

Add Svabensky@EDM'24

← Older revision		Revision as of 20:06, 1 September 2024
Line 1:		Line 1:
			Švábenský et al. (2024) [https://educationaldatamining.org/edm2024/proceedings/2024.EDM-posters.82/2024.EDM-posters.82.pdf pdf]

			* Classification models for predicting grades (worse than an average grade, “unsuccessful”, or equal/better than an average grade, “successful”)
			* Investigating bias based on university students' regional background in the context of the Philippines
			* Demographic groups based on 1 of 5 locations from which students accessed online courses in Canvas
			* Bias evaluation using AUC, weighted F1-score, and MADD showed consistent results across all groups, no unfairness was observed


	Lee and Kizilcec (2020) [https://arxiv.org/pdf/2007.00088.pdf pdf]		Lee and Kizilcec (2020) [https://arxiv.org/pdf/2007.00088.pdf pdf]

Ryan at 13:09, 23 February 2023

2023-02-23T13:09:24Z

← Older revision		Revision as of 09:09, 23 February 2023
Line 54:		Line 54:
	* Predicting whether course grade will be above or below 0.5		* Predicting whether course grade will be above or below 0.5
	* Better prediction for female students in some courses, better prediction for male students in other courses		* Better prediction for female students in some courses, better prediction for male students in other courses
	* Generally ~~better~~ prediction for ~~Australian citizens than foreign nationals~~		* Generally worse prediction for international students

Ryan at 13:07, 23 February 2023

2023-02-23T13:07:30Z

← Older revision		Revision as of 09:07, 23 February 2023
Line 49:		Line 49:
	* A range of over-sampling methods tested		* A range of over-sampling methods tested
	* Regardless of over-sampling method used, course pass/fail performance was moderately better for males		* Regardless of over-sampling method used, course pass/fail performance was moderately better for males


	Deho et al. (2023) [https://files.osf.io/v1/resources/5am9z/providers/osfstorage/63eaf170a3fade041fe7c9db?format=pdf&action=download&direct&version=1]		Deho et al. (2023) [https://files.osf.io/v1/resources/5am9z/providers/osfstorage/63eaf170a3fade041fe7c9db?format=pdf&action=download&direct&version=1]

Ryan: Added Deho et al 2023

2023-02-23T13:07:16Z

Added Deho et al 2023

← Older revision		Revision as of 09:07, 23 February 2023
Line 49:		Line 49:
	* A range of over-sampling methods tested		* A range of over-sampling methods tested
	* Regardless of over-sampling method used, course pass/fail performance was moderately better for males		* Regardless of over-sampling method used, course pass/fail performance was moderately better for males

			Deho et al. (2023) [https://files.osf.io/v1/resources/5am9z/providers/osfstorage/63eaf170a3fade041fe7c9db?format=pdf&action=download&direct&version=1]
			* Predicting whether course grade will be above or below 0.5
			* Better prediction for female students in some courses, better prediction for male students in other courses
			* Generally better prediction for Australian citizens than foreign nationals

Ryan: added Sha et al 2022

2022-08-31T20:23:27Z

added Sha et al 2022

← Older revision		Revision as of 16:23, 31 August 2022
Line 43:		Line 43:
	* Despite comparable accuracy, model tends to overpredict Asian and White students' performance, and underpredict Black, Hispanic, and Native American students' performance		* Despite comparable accuracy, model tends to overpredict Asian and White students' performance, and underpredict Black, Hispanic, and Native American students' performance
	* Several fairness correction methods equalize false positive and false negative rates across groups.		* Several fairness correction methods equalize false positive and false negative rates across groups.


			Sha et al. (2022) [https://ieeexplore.ieee.org/abstract/document/9849852]
			* Predicting course pass/fail with random forest in Open University data
			* A range of over-sampling methods tested
			* Regardless of over-sampling method used, course pass/fail performance was moderately better for males

Ryan: Added Jeong et al (2022)

2022-08-04T20:06:32Z

Added Jeong et al (2022)

← Older revision		Revision as of 16:06, 4 August 2022
Line 37:		Line 37:
	* Poorer performance for first-generation students on course grade prediction for independence and separation, and for some algorithms for GPA prediction as well		* Poorer performance for first-generation students on course grade prediction for independence and separation, and for some algorithms for GPA prediction as well
	* Poorer performance for low-income students in several cases, about 1/3 of cases checked		* Poorer performance for low-income students in several cases, about 1/3 of cases checked


			Jeong et al. (2022) [https://fated2022.github.io/assets/pdf/FATED-2022_paper_Jeong_Racial_Bias_ML_Algs.pdf]
			* Predicting 9th grade math score from academic performance, surveys, and demographic information
			* Despite comparable accuracy, model tends to overpredict Asian and White students' performance, and underpredict Black, Hispanic, and Native American students' performance
			* Several fairness correction methods equalize false positive and false negative rates across groups.

Ryan at 14:53, 13 June 2022

2022-06-13T14:53:48Z

← Older revision		Revision as of 10:53, 13 June 2022
Line 34:		Line 34:
	* Predicting course grades and later GPA at public U.S. university		* Predicting course grades and later GPA at public U.S. university
	* Five algorithms and three metrics (independence, separation, sufficiency) analyzed		* Five algorithms and three metrics (independence, separation, sufficiency) analyzed
	* Poorer performance for Latinx students on course grade prediction for all three metrics;		* Poorer performance for Latinx students on course grade prediction for all three metrics; poorer performance for Latinx students on GPA prediction in terms of independence and sufficiency, but not separation
	poorer performance for Latinx students on GPA prediction in terms of independence and sufficiency, but not separation
	* Poorer performance for first-generation students on course grade prediction for independence and separation, and for some algorithms for GPA prediction as well		* Poorer performance for first-generation students on course grade prediction for independence and separation, and for some algorithms for GPA prediction as well
	* Poorer performance for low-income students in several cases, about 1/3 of cases checked		* Poorer performance for low-income students in several cases, about 1/3 of cases checked

Ryan: added Kung & Yu (2020)

2022-06-13T14:53:23Z

added Kung & Yu (2020)

@@ Line 22: / Line 22: @@
 *Among the algorithms, Naive Bayes had the lowest normalized mutual information value and the highest ABROCA value, or differences between the area under curve
 * Students with self-declared disability were predicted to pass the course more often
 Jiang & Pardos (2021) [https://dl.acm.org/doi/pdf/10.1145/3461702.3462623 pdf]
@@ Line 27: / Line 28: @@
 * Roughly equal accuracy across racial groups
 * Slightly better accuracy (~1%) across racial groups when including race in model

Ryan: Added Jiang & Pardos

2022-05-21T13:11:03Z

Added Jiang & Pardos

← Older revision		Revision as of 09:11, 21 May 2022
Line 21:		Line 21:
	* More male students were predicted to pass the course than female students, but this overestimation was fairly small and not consistent across different algorithms		* More male students were predicted to pass the course than female students, but this overestimation was fairly small and not consistent across different algorithms
	*Among the algorithms, Naive Bayes had the lowest normalized mutual information value and the highest ABROCA value, or differences between the area under curve		*Among the algorithms, Naive Bayes had the lowest normalized mutual information value and the highest ABROCA value, or differences between the area under curve
			* Students with self-declared disability were predicted to pass the course more often

	* ~~Students with self-declared disability were predicted to pass the~~ course ~~with 16-23 percentage points~~ in ~~favor from the training and test set~~		Jiang & Pardos (2021) [https://dl.acm.org/doi/pdf/10.1145/3461702.3462623 pdf]
			* Predicting university course grades using LSTM
			* Roughly equal accuracy across racial groups
			* Slightly better accuracy (~1%) across racial groups when including race in model

Seiyon at 11:49, 18 May 2022

2022-05-18T11:49:38Z

← Older revision		Revision as of 07:49, 18 May 2022
Line 3:		Line 3:
	* Models predicting college success (or median grade or above)		* Models predicting college success (or median grade or above)
	*Random forest algorithms performed significantly worse for underrepresented minority students (URM; American Indian, Black, Hawaiian or Pacific Islander, Hispanic, and Multicultural) than non-URM students (White and Asian), for male students than female students		*Random forest algorithms performed significantly worse for underrepresented minority students (URM; American Indian, Black, Hawaiian or Pacific Islander, Hispanic, and Multicultural) than non-URM students (White and Asian), for male students than female students
	* The fairness of the model, namely demographic parity and equality of opportunity, as well as its accuracy, improved after correcting the threshold values from 0.5 to group-specific values		*Random forest algorithms performed significantly worse for male students than female students
			* The fairness of the model, namely demographic parity and equality of opportunity, as well as its accuracy, improved after correcting the threshold values from 0.5 to group-specific values<br />