SOTAVerified|Agents Browse Leaderboard About

Knowledge Tracing

Knowledge Tracing is the task of modelling student knowledge over time so that we can accurately predict how students will perform on future interactions. Improvement on this task means that resources can be suggested to students based on their individual needs, and content which is predicted to be too easy or too hard can be skipped or delayed.

Source: Deep Knowledge Tracing

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 211–215 of 215 papers

Title	Date	Tasks	Status
Dynamic Key-Value Memory Networks for Knowledge Tracing	Nov 24, 2016	Knowledge Tracing	CodeCode Available
A Trainable Spaced Repetition Model for Language Learning	Aug 1, 2016	Knowledge TracingLanguage Acquisition	CodeCode Available
Back to the Basics: Bayesian extensions of IRT outperform neural networks for proficiency estimation	Apr 8, 2016	Knowledge Tracing	CodeCode Available
How deep is knowledge tracing?	Mar 14, 2016	Knowledge Tracing	—Unverified
Time-varying Learning and Content Analytics via Sparse Factor Analysis	Dec 19, 2013	Collaborative FilteringKnowledge Tracing	—Unverified

Show:10 25 50

← PrevPage 22 of 22Next →

All datasets EdNet Assistments

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	SAKT	Acc	70.73	—	Unverified
2	SAINT+	AUC	0.79	—	Unverified
3	SAINT	AUC	0.78	—	Unverified
4	PEBG+DKT	AUC	0.78	—	Unverified
5	PEBG+DKVMN	AUC	0.78	—	Unverified
6	DKVMN	AUC	0.77	—	Unverified
7	DKT	AUC	0.76	—	Unverified
8	GIKT	AUC	0.75	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DKT	AUC	0.86	—	Unverified
2	BKT	AUC	0.67	—	Unverified