{"url":"/dataset/amazon-product-data","name":"Amazon Product Data","full_name":"rithik","description_markdown":"This dataset contains product reviews and metadata from Amazon, including 142.8 million reviews spanning May 1996 - July 2014.\r\n\r\nThis dataset includes reviews (ratings, text, helpfulness votes), product metadata (descriptions, category information, price, brand, and image features), and links (also viewed/also bought graphs).","description_withheld":null,"homepage":"http://jmcauley.ucsd.edu/data/amazon/","introduced_date":"2016-02-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/ups-and-downs-modeling-the-visual-evolution","title":"Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering","first_author":"Ruining He","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Graphs","url":"/datasets/modality/graphs"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Domain Adaptation","url":"/task/domain-adaptation","datasets_with_task":"/datasets/task/domain-adaptation"},{"name":"Recommendation Systems","url":"/task/recommendation-systems","datasets_with_task":"/datasets/task/recommendation-systems"},{"name":"Stochastic Optimization","url":"/task/stochastic-optimization","datasets_with_task":"/datasets/task/stochastic-optimization"},{"name":"Wildly Unsupervised Domain Adaptation","url":"/task/wildly-unsupervised-domain-adaptation","datasets_with_task":"/datasets/task/wildly-unsupervised-domain-adaptation"},{"name":"Topic Classification","url":"/task/topic-classification","datasets_with_task":"/datasets/task/topic-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Amazon Product Data","Noisy-Amazon (20%)","Noisy-Amazon (45%)"],"data_loaders":[{"repo":"https://github.com/DominikBabiarczyk/purchaseData","url":"https://github.com/DominikBabiarczyk/purchaseData","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":41,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/recommendation-systems-on-amazon-product-data","task":"Recommendation Systems","dataset_variant":"Amazon Product Data","rows":2,"metrics":["AUC","F1"],"first_row_in_archive_order":{"model":"TLSAN","paper":"/paper/tlsan-time-aware-long-and-short-term-1","metrics":{"AUC":"0.9773"},"code_links":[{"title":"TsingZ0/TLSAN","url":"https://github.com/TsingZ0/TLSAN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/domain-adaptation-on-noisy-amazon-20","task":"Domain Adaptation","dataset_variant":"Noisy-Amazon (20%)","rows":1,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"Butterfly","paper":"/paper/butterfly-robust-one-step-approach-towards","metrics":{"Average Accuracy":"71.53"},"code_links":[{"title":"fengliu90/Butterfly","url":"https://github.com/fengliu90/Butterfly"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/domain-adaptation-on-noisy-amazon-45","task":"Domain Adaptation","dataset_variant":"Noisy-Amazon (45%)","rows":1,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"Butterfly","paper":"/paper/butterfly-robust-one-step-approach-towards","metrics":{"Average Accuracy":"56.01"},"code_links":[{"title":"fengliu90/Butterfly","url":"https://github.com/fengliu90/Butterfly"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/wildly-unsupervised-domain-adaptation-on-2","task":"Wildly Unsupervised Domain Adaptation","dataset_variant":"Noisy-Amazon (20%)","rows":1,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"Butterfly","paper":"/paper/butterfly-robust-one-step-approach-towards","metrics":{"Average Accuracy":"71.53"},"code_links":[{"title":"fengliu90/Butterfly","url":"https://github.com/fengliu90/Butterfly"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/wildly-unsupervised-domain-adaptation-on-3","task":"Wildly Unsupervised Domain Adaptation","dataset_variant":"Noisy-Amazon (45%)","rows":1,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"Butterfly","paper":"/paper/butterfly-robust-one-step-approach-towards","metrics":{"Average Accuracy":"56.01"},"code_links":[{"title":"fengliu90/Butterfly","url":"https://github.com/fengliu90/Butterfly"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/tlsan-time-aware-long-and-short-term-1","title":"TLSAN: Time-aware Long- and Short-term Attention Network for Next-item Recommendation","date":"2021-03-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/butterfly-robust-one-step-approach-towards","title":"Butterfly: One-step Approach towards Wildly Unsupervised Domain Adaptation","date":"2019-05-19","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/adaptive-user-modeling-with-long-and-short","title":"Adaptive User Modeling with Long and Short-Term Preferences for Personalized Recommendation","date":"2019-01-01","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":3,"samples_ran":0,"samples_unverified":3,"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."}