{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/automatic-anomaly-detection-in-the-cloud-via","title":"Automatic Anomaly Detection in the Cloud Via Statistical Learning","arxiv_id":"1704.07706","date":"2017-04-24","proceeding":null,"authors":["Jordan Hochenbaum","Owen S. Vallis","Arun Kejariwal"],"abstract":"Performance and high availability have become increasingly important drivers,\namongst other drivers, for user retention in the context of web services such\nas social networks, and web search. Exogenic and/or endogenic factors often\ngive rise to anomalies, making it very challenging to maintain high\navailability, while also delivering high performance. Given that\nservice-oriented architectures (SOA) typically have a large number of services,\nwith each service having a large set of metrics, automatic detection of\nanomalies is non-trivial.\n  Although there exists a large body of prior research in anomaly detection,\nexisting techniques are not applicable in the context of social network data,\nowing to the inherent seasonal and trend components in the time series data.\n  To this end, we developed two novel statistical techniques for automatically\ndetecting anomalies in cloud infrastructure data. Specifically, the techniques\nemploy statistical learning to detect anomalies in both application, and system\nmetrics. Seasonal decomposition is employed to filter the trend and seasonal\ncomponents of the time series, followed by the use of robust statistical\nmetrics -- median and median absolute deviation (MAD) -- to accurately detect\nanomalies, even in the presence of seasonal spikes.\n  We demonstrate the efficacy of the proposed techniques from three different\nperspectives, viz., capacity planning, user behavior, and supervised learning.\nIn particular, we used production data for evaluation, and we report Precision,\nRecall, and F-measure in each case.","url_abs":"http://arxiv.org/abs/1704.07706v1","url_pdf":"http://arxiv.org/pdf/1704.07706v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"automatic-anomaly-detection-in-the-cloud-via","repo_url":"https://github.com/marty90/netlytics","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"automatic-anomaly-detection-in-the-cloud-via","repo_url":"https://github.com/nachonavarro/seasonal-esd-anomaly-detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"automatic-anomaly-detection-in-the-cloud-via","repo_url":"https://github.com/vxld014/S-H-ESD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}