{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/back-to-the-basics-bayesian-extensions-of-irt","title":"Back to the Basics: Bayesian extensions of IRT outperform neural networks for proficiency estimation","arxiv_id":"1604.02336","date":"2016-04-08","proceeding":null,"authors":["Kevin H. Wilson","Yan Karklin","Bojian Han","Chaitanya Ekanadham"],"abstract":"Estimating student proficiency is an important task for computer based\nlearning systems. We compare a family of IRT-based proficiency estimation\nmethods to Deep Knowledge Tracing (DKT), a recently proposed recurrent neural\nnetwork model with promising initial results. We evaluate how well each model\npredicts a student's future response given previous responses using two\npublicly available and one proprietary data set. We find that IRT-based methods\nconsistently matched or outperformed DKT across all data sets at the finest\nlevel of content granularity that was tractable for them to be trained on. A\nhierarchical extension of IRT that captured item grouping structure performed\nbest overall. When data sets included non-trivial autocorrelations in student\nresponse patterns, a temporal extension of IRT improved performance over\nstandard IRT while the RNN-based method did not. We conclude that IRT-based\nmodels provide a simpler, better-performing alternative to existing RNN-based\nmodels of student interaction data while also affording more interpretability\nand guarantees due to their formulation as Bayesian probabilistic models.","url_abs":"http://arxiv.org/abs/1604.02336v2","url_pdf":"http://arxiv.org/pdf/1604.02336v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"back-to-the-basics-bayesian-extensions-of-irt","repo_url":"https://github.com/Knewton/edm2016","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"knowledge-tracing","task_name":"Knowledge Tracing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1604.02336","atlas_url":"https://app.syntology.ai/?focus=1604.02336","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}