Big data analysis can open up valuable insights that are locked up in databases, but releasing that information without access to a team of data scientists isn't easy.
Analytics company Prelert is aiming to make big data accessible and valuable for all businesses with its anomaly detection engine, built using unsupervised machine learning technology. No human intervention is required to set parameters or tell it what to look for, once it's pointed in the right direction it will go to work on massive volumes of streaming data.
The latest stage of its development is today's release of a connector to allow deployment of the technology on Elasticsearch stacks. Offering an Elasticsearch connector, opens up the use of machine learning technology, providing tools that make it easier to identify threats and opportunities hidden within massive data sets.
"Prelert is dedicated to making it easier for users to analyze their data and drive real, actionable value from it", says Mark Jaffe, CEO of Prelert. "The amounts of data that companies and organizations have these days are simply massive -- too massive for humans to process and analyze. The release of our Elasticsearch Connector is the latest step toward making the analysis of large data sets possible, repeatable and valuable without a team of data scientists".
The Anomaly Detective can process large volumes of streaming data, automatically learn normal behavior patterns represented by that data and identify and cross-correlate any anomalies. Add in the ability to processes millions of data points in real-time and it can identify performance, security and operational anomalies so they can be acted on before they have an impact on the business.
The Elasticsearch Connector is written in Python and is available now via GitHub. Additional connectors for other big data technologies are set to be released in the coming months. Meantime you can find more about anomaly detection on Prelert's website.
Photo Credit: T.L. Furrer / Shutterstock