{"id":51512949,"url":"https://github.com/computorg/published-202312-cleynen-local","last_synced_at":"2026-07-08T08:02:56.017Z","repository":{"id":209622700,"uuid":"721261628","full_name":"computorg/published-202312-cleynen-local","owner":"computorg","description":null,"archived":false,"fork":false,"pushed_at":"2026-07-06T09:23:03.000Z","size":33313,"stargazers_count":0,"open_issues_count":3,"forks_count":1,"subscribers_count":4,"default_branch":"main","last_synced_at":"2026-07-06T11:14:47.099Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"http://computo-journal.org/published-202312-cleynen-local/","language":"R","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"cc-by-4.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/computorg.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2023-11-20T17:29:24.000Z","updated_at":"2026-07-06T09:23:08.000Z","dependencies_parsed_at":"2025-06-06T15:33:52.983Z","dependency_job_id":null,"html_url":"https://github.com/computorg/published-202312-cleynen-local","commit_stats":null,"previous_names":["computorg/published-202312-cleynen-local"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/computorg/published-202312-cleynen-local","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/computorg%2Fpublished-202312-cleynen-local","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/computorg%2Fpublished-202312-cleynen-local/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/computorg%2Fpublished-202312-cleynen-local/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/computorg%2Fpublished-202312-cleynen-local/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/computorg","download_url":"https://codeload.github.com/computorg/published-202312-cleynen-local/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/computorg%2Fpublished-202312-cleynen-local/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35257177,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-08T02:00:06.796Z","response_time":61,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-07-08T08:02:55.243Z","updated_at":"2026-07-08T08:02:56.003Z","avatar_url":"https://github.com/computorg.png","language":"R","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Local tree methods for classification: a review and some dead ends\nAlice Cleynen, Louis Raynal, Jean-Michel Marin\n2023-12-14\n\n### Citation\n\nAlice Cleynen, Louis Raynal and Jean-Michel Marin (December 2023). Local tree methods for classification: a review and some dead ends. Computo.\n\u003chttps://doi.org/10.57750/3j8m-8d57\u003e\n\n### Badges\n\n[![build and\npublish](https://github.com/computorg/published-202312-cleynen-local/actions/workflows/build.yml/badge.svg)](https://github.com/computorg/published-202312-cleynen-local/actions/workflows/build.yml)\n[![reviews](https://img.shields.io/badge/review-report-blue)](https://github.com/computorg/published-202312-cleynen-local/issues?q=is%3Aopen+is%3Aissue+label%3Areview)\n[![SWH](https://archive.softwareheritage.org/badge/origin/https://github.com/computorg/published-202312-cleynen-local)](https://archive.softwareheritage.org/browse/origin/?origin_url=https://github.com/computorg/published-202312-cleynen-local)\n[![DOI:10.57750/3j8m-8d57](https://img.shields.io/badge/DOI-10.57750%2F3j8m--8d57-034E79.svg)](https://doi.org/10.57750/3j8m-8d57)\n[![Creative Commons\nLicense](https://i.creativecommons.org/l/by/4.0/80x15.png)](http://creativecommons.org/licenses/by/4.0/)\n\n### Authors’ affiliations\n\n- [Alice Cleynen](https://alice.cleynen.fr/) (IMAG, Univ Montpellier, CNRS, UMR 5149, Montpellier, France)\n- Louis Raynal (Centre Hospitalier Départemental Vendée, La Roche-sur-Yon, France)\n- [Jean-Michel Marin](https://imag.umontpellier.fr/~marin/) (IMAG, Univ Montpellier, CNRS, UMR 5149, Montpellier, France)\n\n### Abstract\n\nRandom Forests (RF) (Breiman 2001) are very popular machine learning\nmethods. They perform well even with little or no tuning, and have some\ntheoretical guarantees, especially for sparse problems (Biau 2012;\nScornet et al. 2015). These learning strategies have been used in\nseveral contexts, also outside the field of classification and\nregression. To perform Bayesian model selection in the case of\nintractable likelihoods, the ABC Random Forests (ABC-RF) strategy of\nPudlo et al. (2016) consists in applying Random Forests on training sets\ncomposed of simulations coming from the Bayesian generative models. The\nABC-RF technique is based on an underlying RF for which the training and\nprediction phases are separated. The training phase does not take into\naccount the data to be predicted. This seems to be suboptimal as in the\nABC framework only one observation is of interest for the prediction. In\nthis paper, we study tree-based methods that are built to predict a\nspecific instance in a classification setting. This type of methods\nfalls within the scope of local (lazy/instance-based/case specific)\nclassification learning. We review some existing strategies and propose\ntwo new ones. The first consists in modifying the tree splitting rule by\nusing kernels, the second in using a first RF to compute some local\nvariable importance that is used to train a second, more local, RF.\nUnfortunately, these approaches, although interesting, do not provide\nconclusive results.\n\n\u003cdiv id=\"refs\" class=\"references csl-bib-body hanging-indent\"\u003e\n\n\u003cdiv id=\"ref-biau:2012\" class=\"csl-entry\"\u003e\n\nBiau, G. 2012. “Analysis of a Random Forest Model.” *Journal of Machine\nLearning Research* 13: 1063–95.\n\n\u003c/div\u003e\n\n\u003cdiv id=\"ref-breiman:2001\" class=\"csl-entry\"\u003e\n\nBreiman, L. 2001. “Random Forests.” *Machine Learning* 45: 5–32.\n\n\u003c/div\u003e\n\n\u003cdiv id=\"ref-pudlo:etal:2016\" class=\"csl-entry\"\u003e\n\nPudlo, P., J.-M. Marin, A. Estoup, J.-M. Cornuet, M. Gautier, and C. P.\nRobert. 2016. “Reliable ABC Model Choice via Random Forests.”\n*Bioinformatics* 32 (6): 859–66.\n\n\u003c/div\u003e\n\n\u003cdiv id=\"ref-scornet:etal:2015\" class=\"csl-entry\"\u003e\n\nScornet, E., G. Biau, and J.-P. Vert. 2015. “Consistency of Random\nForests.” *Annals of Statistics* 43 (4): 1716–41.\n\n\u003c/div\u003e\n\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcomputorg%2Fpublished-202312-cleynen-local","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcomputorg%2Fpublished-202312-cleynen-local","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcomputorg%2Fpublished-202312-cleynen-local/lists"}