The first set of unsupervised machine learning capabilities simplifies anomaly detection for time series use cases MOUNTAIN VIEW, Calif. and AMSTERDAM, The Netherlands, May 04, 2017 (GLOBE NEWSWIRE) -- Elastic, the company behindElasticsearch, and ...
The first set of unsupervised machine learning capabilities simplifies anomaly detection for time series use cases
MOUNTAIN VIEW, Calif. and AMSTERDAM, The Netherlands, May 04, 2017 (GLOBE NEWSWIRE) -- Elastic, the company behind Elasticsearch, and the Elastic Stack, the most widely used collection of open source products for solving mission-critical use cases like search, logging, and analytics, announces the introduction of their first machine learning capabilities in Elastic's 5.4 release. Based on the recent acquisition of Prelert, the new capabilities address the growing desire for customers to utilize machine learning technology, without the need for specialist in-house knowledge and custom development. Elastic's new machine learning features provide a ready-built solution for any time series dataset, which automatically identifies anomalies, streamlines root cause analysis, and reduces false positives within real-time applications. The technology delivers rapid business benefits for companies trying to spot infrastructure problems, cyber attacks, or business issues in real-time.
"Our vision is to take the complexity out and make it simple for our users to deploy machine learning within the Elastic Stack for use cases like logging, security, and metrics," said Shay Banon, Elastic Founder and CEO. "I'm excited that our new unsupervised machine learning capabilities will give our users an out-of-the-box experience, at scale to find anomalies in their time series data, and in a way that is a natural extension of search and analytics."
As organizations seek to derive and operationalize real-time insights, the Elastic Stack has become one of the most widely used tools for developers and IT operations teams to use for collecting, enriching, and analyzing log files, security data, metrics, text documents, and more. However, as the data generated by such organizations increase in size and complexity, traditional approaches to data analysis become impractical. While third-party and off-the-shelf machine learning toolkits may offer capabilities to create statistical models, the biggest challenge lies in developing real-time operational systems for existing workstreams and use cases. Scarce and expensive data science skills are needed to figure-out the correct statistical models for different, diverse data sets, and hand-crafted rules are brittle and often generate many false-positives.
Now available in the 5.4 release as a feature in X-Pack, the first set of Elastic's unsupervised machine learning features automates anomaly detection in time series data, such as log files, application and performance metrics, network flows, or financial/transaction data. By utilizing existing and continuous data stored in Elasticsearch, Elastic's new machine learning capabilities provide users with an out-of-box experience to operationalize their workstreams and use cases like logging, security analytics, and metrics analytics, in real-time, create sophisticated machine learning jobs using a familiar, user-friendly Kibana UI, and minimize complexity and painful integration. Additional benefits include:
- Installs into Elasticsearch and Kibana with a single command as part of X-Pack
- Native integration with the Elastic Stack; no need to move data out of Elasticsearch
- An intuitive UI for creating machine learning jobs and analyzing anomaly detection results across diverse data types (log messages, network traffic, metrics)
- Runs within Elasticsearch - highly scalable and highly available
- Full support for X-Pack's alerting features for proactive notifications
Elastic builds software to make data usable in real time and at scale for search, logging, security, and analytics use cases. Founded in 2012, the company develops the open source Elastic Stack (Elasticsearch, Kibana, Beats, and Logstash), X-Pack (commercial features), and Elastic Cloud (a hosted offering). To date, there have been more than 100 million cumulative downloads. Backed by Benchmark Capital, Index Ventures, and NEA with more than $100 million in funding, Elastic has a distributed workforce with more than 500 employees in 30 countries. Learn more at elastic.co.
Elastic Media Contacts:
Reidy Communications for Elastic
Age of Peers Ltd for Elastic
+44 (0)7899 965232
Elastic Asia Pacific
+852 3552 2927
The issuer of this announcement warrants that they are solely responsible for the content, accuracy and originality of the information contained therein.
Source: Elastic via Globenewswire
Source(s) : Elastic
Professor Erkki Oja wins Nokia Foundation Recognition Award for his pioneering work in machine learning, pattern recognition and neurocomputingPress Release 22 November, 2017 Espoo, Finland - Nokia Foundation has granted its 2017 Recognition Award to professor emeritus Erkki Oja for his contributions to the development of machine learning, pattern recognition and neurocomputing, ...
The ENS Paris-Saclay, Atos and the CEA have created the "Industrial Data Analytics & Machine Learning" ChairThe ENS Paris-Saclay, Atos and the CEA have created the "Industrial Data Analytics & Machine Learning" Chair for the development of a cooperative program oriented towards industrial applications of artificial intelligence The three ...