{"url":"/dataset/astock","name":"Astock","full_name":null,"description_markdown":"(1) provide financial news for each specific stock. (2) provide various stock technical factors and fundamental factors for each stock.","description_withheld":null,"homepage":"https://github.com/JinanZou/Astock","introduced_date":"2022-07-03","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Stock Market Prediction","url":"/task/stock-market-prediction","datasets_with_task":"/datasets/task/stock-market-prediction"},{"name":"Stock Trend Prediction","url":"/task/stock-trend-prediction","datasets_with_task":"/datasets/task/stock-trend-prediction"},{"name":"Stock Prediction","url":"/task/stock-prediction","datasets_with_task":"/datasets/task/stock-prediction"},{"name":"Stock Price Prediction","url":"/task/stock-price-prediction","datasets_with_task":"/datasets/task/stock-price-prediction"},{"name":"Text-Based Stock Prediction","url":"/task/text-based-stock-prediction","datasets_with_task":"/datasets/task/text-based-stock-prediction"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["Astock"],"data_loaders":[],"num_papers_in_archive":11,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/stock-market-prediction-on-astock","task":"Stock Market Prediction","dataset_variant":"Astock","rows":17,"metrics":["Accuray","F1-score","Recall","Precision"],"first_row_in_archive_order":{"model":"SRL&SDPG&Factors","paper":"/paper/finreport-explainable-stock-earnings","metrics":{"Accuray":"75.40","F1-score":"75.12","Precision":"75.42","Recall":"75.23"},"code_links":[{"title":"frinkleko/finreport","url":"https://github.com/frinkleko/finreport"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/stock-price-prediction-on-astock","task":"Stock Price Prediction","dataset_variant":"Astock","rows":1,"metrics":["1-1"],"first_row_in_archive_order":{"model":"SRLP","paper":"/paper/astock-a-new-dataset-and-automated-stock","metrics":{"1-1":"66.89"},"code_links":[{"title":"jinanzou/astock","url":"https://github.com/jinanzou/astock"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/finreport-explainable-stock-earnings","title":"FinReport: Explainable Stock Earnings Forecasting via News Factor Analyzing Model","date":"2024-03-05","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/lert-a-linguistically-motivated-pre-trained","title":"LERT: A Linguistically-motivated Pre-trained Language Model","date":"2022-11-10","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/astock-a-new-dataset-and-automated-stock","title":"Astock: A New Dataset and Automated Stock Trading based on Stock-specific News Analyzing Model","date":"2022-06-14","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/pert-pre-training-bert-with-permuted-language","title":"PERT: Pre-training BERT with Permuted Language Model","date":"2022-03-14","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/skep-sentiment-knowledge-enhanced-pre","title":"SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis","date":"2020-05-12","rows_on_this_dataset":1,"code_links":7,"syntology":null},{"paper":"/paper/revisiting-pre-trained-models-for-chinese","title":"Revisiting Pre-Trained Models for Chinese Natural Language Processing","date":"2020-04-29","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":35,"samples_ran":9,"samples_unverified":26,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","rows_on_this_dataset":2,"code_links":67,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":48,"samples_ran":22,"samples_unverified":26,"pointer_only_for_licence":23,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","rows_on_this_dataset":1,"code_links":534,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":659,"samples_ran":204,"samples_unverified":455,"pointer_only_for_licence":149,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/stock-movement-prediction-from-tweets-and","title":"Stock Movement Prediction from Tweets and Historical Prices","date":"2018-07-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/listening-to-chaotic-whispers-a-deep-learning","title":"Listening to Chaotic Whispers: A Deep Learning Framework for News-oriented Stock Trend Prediction","date":"2017-12-06","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":5,"samples_unverified":1,"pointer_only_for_licence":6,"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":4,"samples_harvested":748,"samples_ran":240,"samples_unverified":508,"pointer_only_for_licence":178,"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."}