Difference between revisions of "Feature-Aware Student knowledge Tracing (FAST)"
(New page: Feature-Aware Student knowledge Tracing (FAST) is a new student model created by PAWs lab and Pearson with the state-of-the-art predictive performance. For the first time it unifies existe...) |
|||
| Line 1: | Line 1: | ||
| − | Feature-Aware Student knowledge Tracing (FAST) is a new student model created by PAWs lab and Pearson with the state-of-the-art predictive performance. For the first time it unifies existed specially designed student models based on [http://liris.cnrs.fr/~pchampin/2014/m2iade-ia2/_static/893CorbettAnderson1995.pdf Knowledge Tracing] framework with integrated advantages: compared with the most popular student model, [http://liris.cnrs.fr/~pchampin/2014/m2iade-ia2/_static/893CorbettAnderson1995.pdf Knowledge Tracing], (1) it improves up to 25% in classification performance, (2) it generates more interpretable, consistent parameters, and (3) it is 300 times faster. In a follow-up study, we compared FAST to the best paper model (a single-purpose model) of the same year with favorable results while FAST is designed as a general-purpose model. The [http://educationaldatamining.org/EDM2014/uploads/procs2014/long%20papers/84_EDM-2014-Full.pdf main paper] was nominated for the Best Paper Award in a top-tier conference in 2014. Both the main and the | + | Feature-Aware Student knowledge Tracing (FAST) is a new student model created by PAWs lab and Pearson with the state-of-the-art predictive performance. For the first time it unifies existed specially designed student models based on [http://liris.cnrs.fr/~pchampin/2014/m2iade-ia2/_static/893CorbettAnderson1995.pdf Knowledge Tracing] framework with integrated advantages: compared with the most popular student model, [http://liris.cnrs.fr/~pchampin/2014/m2iade-ia2/_static/893CorbettAnderson1995.pdf Knowledge Tracing], (1) it improves up to 25% in classification performance, (2) it generates more interpretable, consistent parameters, and (3) it is 300 times faster. In a [[http://adenu.ia.uned.es/workshops/pale2014/pale2014_proceedings_vol1181.pdf#page=9 follow-up study], we compared FAST to the best paper model (a single-purpose model) of the same year with favorable results while FAST is designed as a general-purpose model. The [http://educationaldatamining.org/EDM2014/uploads/procs2014/long%20papers/84_EDM-2014-Full.pdf main paper] was nominated for the Best Paper Award in a top-tier conference in 2014. Both the main and the follow-up papers were cited by top researchers in the field from Carnegie Mellon University, Stanford, Cornell, ETH Zurich (etc.) with in total 34 citations since 2014 (till 04/2016). |
* Download the source code [http://ml-smores.github.io/fast/ here] | * Download the source code [http://ml-smores.github.io/fast/ here] | ||
* Read the conference presentation slides [http://www.slideshare.net/huangyun/fast-presentation-48711687 here] | * Read the conference presentation slides [http://www.slideshare.net/huangyun/fast-presentation-48711687 here] | ||
* Read the tutorial slides presented in EDM 2015 workshop [http://www.slideshare.net/huangyun/2015edm-featureaware-student-knowledge-tracing-tutorial here] | * Read the tutorial slides presented in EDM 2015 workshop [http://www.slideshare.net/huangyun/2015edm-featureaware-student-knowledge-tracing-tutorial here] | ||
Revision as of 03:30, 4 April 2016
Feature-Aware Student knowledge Tracing (FAST) is a new student model created by PAWs lab and Pearson with the state-of-the-art predictive performance. For the first time it unifies existed specially designed student models based on Knowledge Tracing framework with integrated advantages: compared with the most popular student model, Knowledge Tracing, (1) it improves up to 25% in classification performance, (2) it generates more interpretable, consistent parameters, and (3) it is 300 times faster. In a [follow-up study, we compared FAST to the best paper model (a single-purpose model) of the same year with favorable results while FAST is designed as a general-purpose model. The main paper was nominated for the Best Paper Award in a top-tier conference in 2014. Both the main and the follow-up papers were cited by top researchers in the field from Carnegie Mellon University, Stanford, Cornell, ETH Zurich (etc.) with in total 34 citations since 2014 (till 04/2016).
