{"url":"/dataset/heloc","name":"HELOC","full_name":"Home Equity Line of Credit","description_markdown":"# HELOC\r\nThe [HELOC dataset](https://community.fico.com/s/explainable-machine-learning-challenge?tabset-158d9=d157e) from FICO.\r\nEach entry in the dataset is a line of credit, typically offered by a bank as a percentage of home equity (the difference between the current market value of a home and its purchase price).\r\nThe customers in this dataset have requested a credit line in the range of $5,000 - $150,000.\r\nThe fundamental task is to use the information about the applicant in their credit report to predict whether they will repay their HELOC account within 2 years.\r\n\r\n# Configurations and tasks\r\n| **Configuration** | **Task**                  | **Description**                                                 |\r\n|-------------------|---------------------------|-----------------------------------------------------------------|\r\n| risk              | Binary classification     | Will the customer default?                                      |","description_withheld":null,"homepage":"https://www.kaggle.com/datasets/averkiyoliabev/home-equity-line-of-creditheloc","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Tabular","url":"/datasets/modality/tabular"}],"tasks":[{"name":"Tabular Data Generation","url":"/task/tabular-data-generation","datasets_with_task":"/datasets/task/tabular-data-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["HELOC"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/tabular-data-generation-on-heloc","task":"Tabular Data Generation","dataset_variant":"HELOC","rows":6,"metrics":["DT Accuracy","LR Accuracy","Parameters(M)","RF Accuracy"],"first_row_in_archive_order":{"model":"Distill-GReaT","paper":"/paper/language-models-are-realistic-tabular-data","metrics":{"DT Accuracy":"81.4","LR Accuracy":"70.58","Parameters(M)":"82","RF Accuracy":"82.14"},"code_links":[{"title":"kathrinse/be_great","url":"https://github.com/kathrinse/be_great"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/tabular-data-generation-using-binary","title":"Tabular Data Generation using Binary Diffusion","date":"2024-09-20","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":10,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/language-models-are-realistic-tabular-data","title":"Language Models are Realistic Tabular Data Generators","date":"2022-10-12","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/modeling-tabular-data-using-conditional-gan","title":"Modeling Tabular data using Conditional GAN","date":"2019-07-01","rows_on_this_dataset":3,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":19,"samples_ran":12,"samples_unverified":7,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}