Indigenous Learners in North America - Revision history

Ryan: Added Jeong et al (2022)

2022-08-04T20:05:54Z

Added Jeong et al (2022)

← Older revision		Revision as of 16:05, 4 August 2022
Line 15:		Line 15:
	* Roughly equal accuracy across racial groups (including Native American and Pacific Islander students)		* Roughly equal accuracy across racial groups (including Native American and Pacific Islander students)
	* Slightly better accuracy (~1%) across racial groups when including race in model		* Slightly better accuracy (~1%) across racial groups when including race in model


			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 underpredict Native American students' performance
			* Several fairness correction methods equalize false positive and false negative rates across groups.

Ryan: re-ordering

2022-06-10T10:03:53Z

re-ordering

← Older revision		Revision as of 06:03, 10 June 2022
Line 7:		Line 7:
	Christie et al. (2019) [https://files.eric.ed.gov/fulltext/ED599217.pdf pdf]		Christie et al. (2019) [https://files.eric.ed.gov/fulltext/ED599217.pdf pdf]
	*Models predicting student's high school dropout		*Models predicting student's high school dropout
	*The decision trees showed little difference in AUC among White, Black, Hispanic, Asian~~, American Indian and Alaska Native~~, and Native Hawaiian and Pacific Islander.		*The decision trees showed little difference in AUC among American Indian and Alaska Native, White, Black, Hispanic, Asian, and Native Hawaiian and Pacific Islander.
	*The decision trees showed very minor differences in AUC between female and male students		*The decision trees showed very minor differences in AUC between female and male students

Ryan: Added Jiang & Pardos

2022-05-21T13:03:46Z

Added Jiang & Pardos

← Older revision		Revision as of 09:03, 21 May 2022
Line 9:		Line 9:
	*The decision trees showed little difference in AUC among White, Black, Hispanic, Asian, American Indian and Alaska Native, and Native Hawaiian and Pacific Islander.		*The decision trees showed little difference in AUC among White, Black, Hispanic, Asian, American Indian and Alaska Native, and Native Hawaiian and Pacific Islander.
	*The decision trees showed very minor differences in AUC between female and male students		*The decision trees showed very minor differences in AUC between female and male students


			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 (including Native American and Pacific Islander students)
			* Slightly better accuracy (~1%) across racial groups when including race in model

Seiyon at 11:44, 18 May 2022

2022-05-18T11:44:23Z

← Older revision		Revision as of 07:44, 18 May 2022
Line 1:		Line 1:
	Lee and Kizilcec (2020) [[https://arxiv.org/pdf/2007.00088.pdf pdf]]		Lee and Kizilcec (2020) [https://arxiv.org/pdf/2007.00088.pdf pdf]
	*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)		*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)
	*The fairness of the model, namely demographic parity and equality of opportunity, as well as its accuracy, improved after correcting the threshold values		*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

Seiyon at 20:18, 28 March 2022

2022-03-28T20:18:03Z

← Older revision		Revision as of 16:18, 28 March 2022
Line 3:		Line 3:
	*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)		*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)
	*The fairness of the model, namely demographic parity and equality of opportunity, as well as its accuracy, improved after correcting the threshold values		*The fairness of the model, namely demographic parity and equality of opportunity, as well as its accuracy, improved after correcting the threshold values


			Christie et al. (2019) [https://files.eric.ed.gov/fulltext/ED599217.pdf pdf]
			*Models predicting student's high school dropout
			*The decision trees showed little difference in AUC among White, Black, Hispanic, Asian, American Indian and Alaska Native, and Native Hawaiian and Pacific Islander.
			*The decision trees showed very minor differences in AUC between female and male students

Seiyon at 00:28, 23 March 2022

2022-03-23T00:28:57Z

← Older revision	Revision as of 20:28, 22 March 2022
Line 1:	Line 1:
		Lee and Kizilcec (2020) [[https://arxiv.org/pdf/2007.00088.pdf pdf]]
		*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)
		*The fairness of the model, namely demographic parity and equality of opportunity, as well as its accuracy, improved after correcting the threshold values

Seiyon: Blanked the page

2022-01-24T05:00:33Z

Blanked the page

← Older revision		Revision as of 01:00, 24 January 2022
Line 1:		Line 1:
	~~Lee and Kizilcec (2020) [[https://arxiv.org/pdf/2007.00088.pdf pdf]]~~
	* Model predicting college course grade of median or above
	* Out-of-the-box random forest model violates demographic parity and equality of opportunity for URM(underrepresented minority: American Indian, Black, Hawaiian or Pacific Islander, Hispanic, and Multicultural) than for non-URM students (White and Asian)

Seiyon: Created page with "Lee and Kizilcec (2020) https://arxiv.org/pdf/2007.00088.pdf pdf * Model predicting college course grade of median or above * Out-of-the-box random forest model violates demographic parity and equality of opportunity for URM(underrepresented minority: American Indian, Black, Hawaiian or Pacific Islander, Hispanic, and Multicultural) than for non-URM students (White and Asian)"

2022-01-24T03:42:27Z

Created page with "Lee and Kizilcec (2020) https://arxiv.org/pdf/2007.00088.pdf pdf * Model predicting college course grade of median or above * Out-of-the-box random forest model violates demographic parity and equality of opportunity for URM(underrepresented minority: American Indian, Black, Hawaiian or Pacific Islander, Hispanic, and Multicultural) than for non-URM students (White and Asian)"

New page

Lee and Kizilcec (2020) [[https://arxiv.org/pdf/2007.00088.pdf pdf]]
* Model predicting college course grade of median or above
* Out-of-the-box random forest model violates demographic parity and equality of opportunity for URM(underrepresented minority: American Indian, Black, Hawaiian or Pacific Islander, Hispanic, and Multicultural) than for non-URM students (White and Asian)