{"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/strict-very-fast-decision-tree-a-memory","title":"Strict Very Fast Decision Tree: a memory conservative algorithm for data stream mining","arxiv_id":"1805.06368","date":"2018-05-16","proceeding":null,"authors":["Victor Guilherme Turrisi da Costa","André Carlos Ponce de Leon Ferreira de Carvalho","Sylvio Barbon Junior"],"abstract":"Dealing with memory and time constraints are current challenges when learning\nfrom data streams with a massive amount of data. Many algorithms have been\nproposed to handle these difficulties, among them, the Very Fast Decision Tree\n(VFDT) algorithm. Although the VFDT has been widely used in data stream mining,\nin the last years, several authors have suggested modifications to increase its\nperformance, putting aside memory concerns by proposing memory-costly\nsolutions. Besides, most data stream mining solutions have been centred around\nensembles, which combine the memory costs of their weak learners, usually\nVFDTs. To reduce the memory cost, keeping the predictive performance, this\nstudy proposes the Strict VFDT (SVFDT), a novel algorithm based on the VFDT.\nThe SVFDT algorithm minimises unnecessary tree growth, substantially reducing\nmemory usage and keeping competitive predictive performance. Moreover, since it\ncreates much more shallow trees than VFDT, SVFDT can achieve a shorter\nprocessing time. Experiments were carried out comparing the SVFDT with the VFDT\nin 11 benchmark data stream datasets. This comparison assessed the trade-off\nbetween accuracy, memory, and processing time. Statistical analysis showed that\nthe proposed algorithm obtained similar predictive performance and\nsignificantly reduced processing time and memory use. Thus, SVFDT is a suitable\noption for data stream mining with memory and time limitations, recommended as\na weak learner in ensemble-based solutions.","url_abs":"http://arxiv.org/abs/1805.06368v2","url_pdf":"http://arxiv.org/pdf/1805.06368v2.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":"strict-very-fast-decision-tree-a-memory","repo_url":"https://github.com/vturrisi/pystream","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":"https://app.syntology.ai/?focus=1805.06368","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}