{"url":"/dataset/nab","name":"NAB","full_name":"Numenta Anomaly Benchmark","description_markdown":"**The First Temporal Benchmark Designed to Evaluate  Real-time Anomaly Detectors Benchmark**\r\n\r\nThe growth of the Internet of Things has created an abundance of streaming data. Finding anomalies in this data can provide valuable insights into opportunities or failures. Yet it’s difficult to achieve, due to the need to process data in real time, continuously learn and make predictions. How do we evaluate and compare various real-time anomaly detection techniques? \r\n\r\nThe Numenta Anomaly Benchmark (NAB) provides a standard, open source framework for evaluating real-time anomaly detection algorithms on streaming data. Through a controlled, repeatable environment of open-source tools, NAB rewards detectors that find anomalies as soon as possible, trigger no false alarms, and automatically adapt to any changing statistics. \r\n\r\nNAB comprises two main components: a scoring system designed for streaming data and a dataset with labeled, real-world time-series data.\r\n\r\nSource: [Evaluating Real-time Anomaly Detection Algorithms – the Numenta Anomaly Benchmark](http://arxiv.org/abs/1510.03336)\r\nImage Source: [https://numenta.com/machine-intelligence-technology/numenta-anomaly-benchmark/](https://numenta.com/machine-intelligence-technology/numenta-anomaly-benchmark/)","description_withheld":null,"homepage":"https://github.com/numenta/NAB","introduced_date":"2015-10-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/evaluating-real-time-anomaly-detection","title":"Evaluating Real-time Anomaly Detection Algorithms - the Numenta Anomaly Benchmark","first_author":"Alexander Lavin","url":null},"license":{"name":"GNU Affero General Public License v3.0","url":"https://zenodo.org/record/3571294#.YFONuGT7S_w"},"modalities":[{"name":"Time series","url":"/datasets/modality/time-series"}],"tasks":[{"name":"Anomaly Detection","url":"/task/anomaly-detection","datasets_with_task":"/datasets/task/anomaly-detection"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Numenta Anomaly Benchmark","NAB"],"data_loaders":[{"repo":"https://github.com/numenta/NAB","url":"https://github.com/numenta/NAB","frameworks":[]}],"num_papers_in_archive":66,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/anomaly-detection-on-numenta-anomaly","task":"Anomaly Detection","dataset_variant":"Numenta Anomaly Benchmark","rows":10,"metrics":["NAB score"],"first_row_in_archive_order":{"model":"HTM AL","paper":"/paper/unsupervised-real-time-anomaly-detection-for","metrics":{"NAB score":"70.1"},"code_links":[{"title":"numenta/NAB","url":"https://github.com/numenta/NAB"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/online-forecasting-and-anomaly-detection","title":"Online Forecasting and Anomaly Detection Based on the ARIMA Model","date":"2021-04-02","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/unsupervised-real-time-anomaly-detection-for","title":"Unsupervised real-time anomaly detection for streaming data","date":"2017-06-02","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/real-time-anomaly-detection-for-streaming","title":"Real-Time Anomaly Detection for Streaming Analytics","date":"2016-07-08","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"paper":"/paper/evaluating-real-time-anomaly-detection","title":"Evaluating Real-time Anomaly Detection Algorithms - the Numenta Anomaly Benchmark","date":"2015-10-12","rows_on_this_dataset":4,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":18,"samples_ran":0,"samples_unverified":18,"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":1,"samples_harvested":18,"samples_ran":0,"samples_unverified":18,"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."}