{"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/entity-embeddings-of-categorical-variables","title":"Entity Embeddings of Categorical Variables","arxiv_id":"1604.06737","date":"2016-04-22","proceeding":null,"authors":["Cheng Guo","Felix Berkhahn"],"abstract":"We map categorical variables in a function approximation problem into\nEuclidean spaces, which are the entity embeddings of the categorical variables.\nThe mapping is learned by a neural network during the standard supervised\ntraining process. Entity embedding not only reduces memory usage and speeds up\nneural networks compared with one-hot encoding, but more importantly by mapping\nsimilar values close to each other in the embedding space it reveals the\nintrinsic properties of the categorical variables. We applied it successfully\nin a recent Kaggle competition and were able to reach the third position with\nrelative simple features. We further demonstrate in this paper that entity\nembedding helps the neural network to generalize better when the data is sparse\nand statistics is unknown. Thus it is especially useful for datasets with lots\nof high cardinality features, where other methods tend to overfit. We also\ndemonstrate that the embeddings obtained from the trained neural network boost\nthe performance of all tested machine learning methods considerably when used\nas the input features instead. As entity embedding defines a distance measure\nfor categorical variables it can be used for visualizing categorical data and\nfor data clustering.","url_abs":"http://arxiv.org/abs/1604.06737v1","url_pdf":"http://arxiv.org/pdf/1604.06737v1.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":"entity-embeddings-of-categorical-variables","repo_url":"https://github.com/entron/entity-embedding-rossmann","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"entity-embeddings-of-categorical-variables","repo_url":"https://github.com/Aditya-Jha2002/Diabetes-Prediction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"entity-embeddings-of-categorical-variables","repo_url":"https://github.com/QuantumAbyss/EntityEmbeddings","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"entity-embeddings-of-categorical-variables","repo_url":"https://github.com/btjones-me/fraud-pycaret-demonstration","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"entity-embeddings-of-categorical-variables","repo_url":"https://github.com/grapestone5321/Kaggle-Abhishek_Thakur","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"entity-embeddings-of-categorical-variables","repo_url":"https://github.com/inzva/sales-prediction-kaggle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"entity-embeddings-of-categorical-variables","repo_url":"https://github.com/samuelli97/cancer_survivability","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"entity-embeddings-of-categorical-variables","repo_url":"https://github.com/DataCanvasIO/DeepTables","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"entity-embeddings","task_name":"Entity Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1604.06737","atlas_url":"https://app.syntology.ai/?focus=1604.06737","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06737"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Aditya-Jha2002/Diabetes-Prediction","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/samuelli97/cancer_survivability","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/QuantumAbyss/EntityEmbeddings","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/entron/entity-embedding-rossmann","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DataCanvasIO/DeepTables","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/grapestone5321/Kaggle-Abhishek_Thakur","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/inzva/sales-prediction-kaggle","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/btjones-me/fraud-pycaret-demonstration","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"bf264f7010c153fe","entry":"evaluate_models","repo":"entron/entity-embedding-rossmann","repo_kind":"official","path":"train_test_model.py","file_url":"https://github.com/entron/entity-embedding-rossmann/blob/HEAD/train_test_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bf264f7010c153fe"}},{"code_sha256_prefix":"fc200c8461bd4fe6","entry":"sample","repo":"entron/entity-embedding-rossmann","repo_kind":"official","path":"train_test_model.py","file_url":"https://github.com/entron/entity-embedding-rossmann/blob/HEAD/train_test_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fc200c8461bd4fe6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}