EdNet is the dataset of all student-system interactions collected over 2 years by Santa a multi-platform AI tutoring service with more than 780K users in Korea available through Android, iOS and web.
In EdNet, there are four datasets named KT1, KT2, KT3, and KT4 with different extents. In this challenge, we only use EdNet-KT1 datasets consist of students’ question-solving logs, which is the most basic and fundamental information that can be used by various deep-learning knowledge tracing models.
EdNet paper (Choi et al. '19)The EdNet is publicly released under CC BY-NC 4.0 license for research purposes. The EdNet-KT1 dataset can be downloaded below.
Ask us questions at research@riiid.co.
We thank the SQuAD team for allowing us to use their code and templates for generating this website.
| Rank | Model | ACC | AUC |
|---|---|---|---|
| 1 Jan 06, 2020 | SAINT Riiid! | 0.7368 | 0.7811 |
| 2 Jan 06, 2020 | SSAKT Riiid! | 0.7340 | 0.7777 |
| 3 Jan 06, 2020 | LTMTI Riiid! | 0.7339 | 0.7762 |
| 4 Jan 06, 2020 | UTMTI Riiid! | 0.7323 | 0.7735 |
| 5 Jan 06, 2020 | NPA Riiid! https://arxiv.org/abs/1906.10910 | 0.7290 | 0.7363 |
| 6 Jan 06, 2020 | SAKT Riiid! (Pandey et al, 2019) https://arxiv.org/abs/1907.06837 | 0.7271 | 0.7671 |
| 7 Jan 06, 2020 | MF Riiid! | 0.6822 | 0.7163 |