{"url":"/dataset/antm2c","name":"AntM2C","full_name":"Ant-Group Multi-Scenario Multi-Modal CTR dataset","description_markdown":"We release  a large-scale Multi-Scenario Multi-Modal CTR dataset\r\nnamed AntM2C, built from real industrial data from Alipay. This\r\ndataset offers an impressive breadth and depth of information, covering CTR data from four diverse business scenarios, including advertisements, consumer coupons, mini-programs, and videos. Unlike existing datasets, AntM2C provides not only ID-based features\r\nbut also five textual features and one image feature for both users\r\nand items, supporting more delicate multi-modal CTR prediction.\r\n\r\nThis dataset is from 110 million user exposure-click samples in 5 scenarios on the Alipay APP, including 670,000 users and 180,000 items, with 37 features. For more detailed information, please see the homepage: https://www.atecup.cn/dataSetDetailOpen/1","description_withheld":null,"homepage":"https://www.atecup.cn/dataSetDetailOpen/1","introduced_date":"2024-04-17","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Tabular","url":"/datasets/modality/tabular"}],"tasks":[{"name":"Recommendation Systems","url":"/task/recommendation-systems","datasets_with_task":"/datasets/task/recommendation-systems"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["AntM2C"],"data_loaders":[],"num_papers_in_archive":0,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"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."}