{"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/assessing-binary-classifiers-using-only","title":"Assessing binary classifiers using only positive and unlabeled data","arxiv_id":"1504.06837","date":"2015-04-26","proceeding":null,"authors":["Marc Claesen","Jesse Davis","Frank De Smet","Bart De Moor"],"abstract":"Assessing the performance of a learned model is a crucial part of machine\nlearning. However, in some domains only positive and unlabeled examples are\navailable, which prohibits the use of most standard evaluation metrics. We\npropose an approach to estimate any metric based on contingency tables,\nincluding ROC and PR curves, using only positive and unlabeled data. Estimating\nthese performance metrics is essentially reduced to estimating the fraction of\n(latent) positives in the unlabeled set, assuming known positives are a random\nsample of all positives. We provide theoretical bounds on the quality of our\nestimates, illustrate the importance of estimating the fraction of positives in\nthe unlabeled set and demonstrate empirically that we are able to reliably\nestimate ROC and PR curves on real data.","url_abs":"http://arxiv.org/abs/1504.06837v2","url_pdf":"http://arxiv.org/pdf/1504.06837v2.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":"assessing-binary-classifiers-using-only","repo_url":"https://github.com/claesenm/semisup-metrics","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"assessing-binary-classifiers-using-only","repo_url":"https://github.com/phuijse/bagging_pu","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}