{"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/a-benchmark-of-categorical-encoders-for-1","title":"A benchmark of categorical encoders for binary classification","arxiv_id":"2307.09191","date":"2023-07-17","proceeding":"NeurIPS 2023 11","authors":["Federico Matteucci","Vadim Arzamasov","Klemens Boehm"],"abstract":"Categorical encoders transform categorical features into numerical representations that are indispensable for a wide range of machine learning models. Existing encoder benchmark studies lack generalizability because of their limited choice of (1) encoders, (2) experimental factors, and (3) datasets. Additionally, inconsistencies arise from the adoption of varying aggregation strategies. This paper is the most comprehensive benchmark of categorical encoders to date, including an extensive evaluation of 32 configurations of encoders from diverse families, with 36 combinations of experimental factors, and on 50 datasets. The study shows the profound influence of dataset selection, experimental factors, and aggregation strategies on the benchmark's conclusions -- aspects disregarded in previous encoder benchmarks.","url_abs":"https://arxiv.org/abs/2307.09191v3","url_pdf":"https://arxiv.org/pdf/2307.09191v3.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":"a-benchmark-of-categorical-encoders-for-1","repo_url":"https://github.com/drcohomology/encoderbenchmarking","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"classification-1","task_name":"Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2307.09191","atlas_url":"https://app.syntology.ai/?focus=2307.09191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09191"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/DrCohomology/EncoderBenchmarking","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/drcohomology/encoderbenchmarking","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":9},"by_repo_kind":{"official":{"samples":9,"ran":9,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"4adfcc2981cd3803","entry":"get_disjoint_samples","repo":"DrCohomology/EncoderBenchmarking","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/DrCohomology/EncoderBenchmarking/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4adfcc2981cd3803"}},{"code_sha256_prefix":"29cd9c8f26fb6da7","entry":"get_disjoint_samples_bootstrap","repo":"DrCohomology/EncoderBenchmarking","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/DrCohomology/EncoderBenchmarking/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"29cd9c8f26fb6da7"}},{"code_sha256_prefix":"d518a6dfbf88372e","entry":"get_relation_properties","repo":"DrCohomology/EncoderBenchmarking","repo_kind":"official","path":"src/relation_utils.py","file_url":"https://github.com/DrCohomology/EncoderBenchmarking/blob/HEAD/src/relation_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d518a6dfbf88372e"}},{"code_sha256_prefix":"e49275c800f47936","entry":"jaccard","repo":"DrCohomology/EncoderBenchmarking","repo_kind":"official","path":"src/rank_metrics.py","file_url":"https://github.com/DrCohomology/EncoderBenchmarking/blob/HEAD/src/rank_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e49275c800f47936"}},{"code_sha256_prefix":"7dfb47f5f62d013d","entry":"jaccard_best","repo":"DrCohomology/EncoderBenchmarking","repo_kind":"official","path":"src/rank_metrics.py","file_url":"https://github.com/DrCohomology/EncoderBenchmarking/blob/HEAD/src/rank_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7dfb47f5f62d013d"}},{"code_sha256_prefix":"4ceb6e77d5114710","entry":"jaccard_worst","repo":"DrCohomology/EncoderBenchmarking","repo_kind":"official","path":"src/rank_metrics.py","file_url":"https://github.com/DrCohomology/EncoderBenchmarking/blob/HEAD/src/rank_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4ceb6e77d5114710"}},{"code_sha256_prefix":"76f37f16642cd78c","entry":"rf2mat","repo":"DrCohomology/EncoderBenchmarking","repo_kind":"official","path":"src/relation_utils.py","file_url":"https://github.com/DrCohomology/EncoderBenchmarking/blob/HEAD/src/relation_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"76f37f16642cd78c"}},{"code_sha256_prefix":"fb563aeae74088ce","entry":"score2rf","repo":"DrCohomology/EncoderBenchmarking","repo_kind":"official","path":"src/relation_utils.py","file_url":"https://github.com/DrCohomology/EncoderBenchmarking/blob/HEAD/src/relation_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fb563aeae74088ce"}},{"code_sha256_prefix":"88a726d9b8653524","entry":"smart_sort","repo":"DrCohomology/EncoderBenchmarking","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/DrCohomology/EncoderBenchmarking/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88a726d9b8653524"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}