{"url":"/dataset/criteo","name":"Criteo","full_name":"Display Advertising Challenge","description_markdown":"**Criteo** contains 7 days of click-through data, which is widely used for CTR prediction benchmarking. There are 26 anonymous categorical fields and 13 continuous fields in Criteo dataset.\n\nSource: [AMER: Automatic Behavior Modeling and Interaction Exploration in Recommender System](https://arxiv.org/abs/2006.05933)\nImage Source: [https://www.kaggle.com/c/criteo-display-ad-challenge](https://www.kaggle.com/c/criteo-display-ad-challenge)","description_withheld":null,"homepage":"https://labs.criteo.com/2013/12/download-terabyte-click-logs/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Click-Through Rate Prediction","url":"/task/click-through-rate-prediction","datasets_with_task":"/datasets/task/click-through-rate-prediction"}],"languages":[],"variants":["Criteo"],"data_loaders":[{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/criteo","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/alibaba/easyrec","url":"https://github.com/alibaba/easyrec","frameworks":[]}],"num_papers_in_archive":46,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/click-through-rate-prediction-on-criteo","task":"Click-Through Rate Prediction","dataset_variant":"Criteo","rows":39,"metrics":["AUC","Log Loss"],"first_row_in_archive_order":{"model":"QNN-α","paper":"/paper/revisiting-feature-interactions-from-the","metrics":{"AUC":"0.8163","Log Loss":"0.4358"},"code_links":[{"title":"salmon1802/QNN","url":"https://github.com/salmon1802/QNN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/revisiting-feature-interactions-from-the","title":"Revisiting Feature Interactions from the Perspective of Quadratic Neural Networks for Click-through Rate Prediction","date":"2025-05-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dcnv3-towards-next-generation-deep-cross","title":"FCN: Fusing Exponential and Linear Cross Network for Click-Through Rate Prediction","date":"2024-07-18","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/tf4ctr-twin-focus-framework-for-ctr","title":"TF4CTR: Twin Focus Framework for CTR Prediction via Adaptive Sample Differentiation","date":"2024-05-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cetn-contrast-enhanced-through-network-for","title":"CETN: Contrast-enhanced Through Network for CTR Prediction","date":"2023-12-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/towards-deeper-lighter-and-interpretable-1","title":"Towards Deeper, Lighter and Interpretable Cross Network for CTR Prediction","date":"2023-11-08","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/stec-see-through-transformer-based-encoder","title":"STEC: See-Through Transformer-based Encoder for CTR Prediction","date":"2023-08-29","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/mmbattn-max-mean-and-bit-wise-attention-for","title":"MMBAttn: Max-Mean and Bit-wise Attention for CTR Prediction","date":"2023-08-25","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/weighted-multi-level-feature-factorization","title":"Weighted Multi-Level Feature Factorization for App ads CTR and installation prediction","date":"2023-08-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cognitive-evolutionary-search-to-select","title":"Cognitive Evolutionary Search to Select Feature Interactions for Click-Through Rate Prediction","date":"2023-08-01","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/finalmlp-an-enhanced-two-stream-mlp-model-for-1","title":"FinalMLP: An Enhanced Two-Stream MLP Model for CTR Prediction","date":"2023-04-03","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":16,"samples_ran":13,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/optimizing-feature-set-for-click-through-rate","title":"Optimizing Feature Set for Click-Through Rate Prediction","date":"2023-01-26","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":1,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/memonet-memorizing-representations-of-all","title":"MemoNet: Memorizing All Cross Features' Representations Efficiently via Multi-Hash Codebook Network for CTR Prediction","date":"2022-10-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/clustering-embedding-tables-without-first","title":"Clustering the Sketch: A Novel Approach to Embedding Table Compression","date":"2022-10-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fibinet-improving-fibinet-by-greatly-reducing","title":"FiBiNet++: Reducing Model Size by Low Rank Feature Interaction Layer for CTR Prediction","date":"2022-09-12","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/optembed-learning-optimal-embedding-table-for","title":"OptEmbed: Learning Optimal Embedding Table for Click-through Rate Prediction","date":"2022-08-09","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/memorize-factorize-or-be-naive-learning","title":"Memorize, Factorize, or be Naïve: Learning Optimal Feature Interaction Methods for CTR Prediction","date":"2021-08-03","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":0,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/contextnet-a-click-through-rate-prediction","title":"ContextNet: A Click-Through Rate Prediction Framework Using Contextual information to Refine Feature Embedding","date":"2021-07-26","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/xcrossnet-feature-structure-oriented-learning","title":"XCrossNet: Feature Structure-Oriented Learning for Click-Through Rate Prediction","date":"2021-04-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/masknet-introducing-feature-wise","title":"MaskNet: Introducing Feature-Wise Multiplication to CTR Ranking Models by Instance-Guided Mask","date":"2021-02-09","rows_on_this_dataset":1,"code_links":21,"syntology":null},{"paper":"/paper/dcn-m-improved-deep-cross-network-for-feature","title":"DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems","date":"2020-08-19","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":2,"samples_unverified":12,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/gatenet-gating-enhanced-deep-network-for","title":"GateNet: Gating-Enhanced Deep Network for Click-Through Rate Prediction","date":"2020-07-06","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/tfnet-multi-semantic-feature-interaction-for","title":"TFNet: Multi-Semantic Feature Interaction for CTR Prediction","date":"2020-06-29","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/correct-normalization-matters-understanding","title":"Correct Normalization Matters: Understanding the Effect of Normalization On Deep Neural Network Models For Click-Through Rate Prediction","date":"2020-06-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/feature-interaction-based-neural-network-for","title":"Feature Interaction based Neural Network for Click-Through Rate Prediction","date":"2020-06-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/autofis-automatic-feature-interaction","title":"AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction","date":"2020-03-25","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":24,"samples_ran":1,"samples_unverified":23,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-sparse-deep-factorization-machine-for","title":"DeepLight: Deep Lightweight Feature Interactions for Accelerating CTR Predictions in Ad Serving","date":"2020-02-17","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/fi-gnn-modeling-feature-interactions-via","title":"Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction","date":"2019-10-12","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/adaptive-factorization-network-learning","title":"Adaptive Factorization Network: Learning Adaptive-Order Feature Interactions","date":"2019-09-07","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fibinet-combining-feature-importance-and","title":"FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction","date":"2019-05-23","rows_on_this_dataset":1,"code_links":31,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":26,"samples_ran":2,"samples_unverified":24,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fat-deepffm-field-attentive-deep-field-aware","title":"FAT-DeepFFM: Field Attentive Deep Field-aware Factorization Machine","date":"2019-05-15","rows_on_this_dataset":1,"code_links":12,"syntology":null},{"paper":"/paper/autoint-automatic-feature-interaction","title":"AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks","date":"2018-10-29","rows_on_this_dataset":1,"code_links":19,"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/xdeepfm-combining-explicit-and-implicit","title":"xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems","date":"2018-03-14","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":3,"samples_unverified":12,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deepfm-a-factorization-machine-based-neural","title":"DeepFM: A Factorization-Machine based Neural Network for CTR Prediction","date":"2017-03-13","rows_on_this_dataset":1,"code_links":23,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":2,"samples_unverified":6,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/product-based-neural-networks-for-user","title":"Product-based Neural Networks for User Response Prediction","date":"2016-11-01","rows_on_this_dataset":3,"code_links":11,"syntology":null},{"paper":"/paper/wide-deep-learning-for-recommender-systems","title":"Wide & Deep Learning for Recommender Systems","date":"2016-06-24","rows_on_this_dataset":1,"code_links":39,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-learning-over-multi-field-categorical","title":"Deep Learning over Multi-field Categorical Data: A Case Study on User Response Prediction","date":"2016-01-11","rows_on_this_dataset":1,"code_links":5,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":13,"samples_harvested":133,"samples_ran":24,"samples_unverified":109,"pointer_only_for_licence":17,"papers_with_no_sample_that_ran":6,"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."}