Journal of Big Data

Table 2 Comparative analysis of baseline models and APP-TGN in identifying students who are at risk in terms of ACC, F1, and REL

From: Enhancing academic performance prediction with temporal graph networks for massive open online courses

Tasks	Metrics	ProbSAP	CNN-LSTM	OMLP	HRNs	MTGNN	AP-GT	APP-TGN1	APP-TGN
Pass/Fail	ACC	77.80	80.10	76.60	79.29	80.21	80.38	82.66	83.22*
	F1	65.41	67.92	64.98	65.74	69.89	70.18	71.23	73.11*
	REL	63.11	73.15	60.47	64.38	73.53	79.55	87.85	90.21*
Pass/Withdrawn	ACC	70.50	72.26	69.36	71.71	72.63	73.21	75.13	77.06*
	F1	72.02	75.94	71.81	72.65	76.03	76.48	77.21	79.70*
	REL	67.53	70.12	50.62	68.34	71.40	74.03	78.25	82.43*

An asterisk (\(*\)) denotes improvements that are statistically significant when compared to the best performing baseline. These improvements are validated by a two-sided t-test with a p-value less than \(10^{-3}\), confirming their statistical significance

Back to article page