TMCnet News

Numenta Ships New HTM Example App: Grok for Stocks
[July 08, 2015]

Numenta Ships New HTM Example App: Grok for Stocks


Numenta, Inc., today announced the availability of Grok for Stocks, the newest example application showing how Hierarchical Temporal Memory (HTM) technology can be applied to streaming data and the Internet of Things.

This Smart News Release features multimedia. View the full release here: http://www.businesswire.com/news/home/20150708005360/en/

Grok for Stocks is a mobile application that continually monitors stock price, stock volume, and Twitter (News - Alert) activity for hundreds of publicly traded companies. Grok for Stocks learns the normal patterns for each company and notifies you if something unusual is happening to any of the companies.

During the past two years, Numenta has created a series of example applications to illustrate the capabilities of HTM. The first application, Grok for IT Analytics, uses HTM to detect anomalies in AWS server metrics and is available on the Amazon Web Services Marketplace. Numenta also published example source code that uses HTM to detect anomalies in human behavior and in GPS tracking data.



"Grok for Stocks is our most accessible demonstration of Numenta HTM technology," said Numenta CEO Donna Dubinsky. "Until now, it has required programming expertise to experience HTM-based anomaly detection. With Grok for Stocks, it is as simple as downloading the app to your smartphone from the Google Play store."

In keeping with its mission to be a technology provider, Numenta is providing the source code for Grok for Stocks under an open source license at: https://github.com/numenta/numenta-apps. Said Dubinsky, "We encourage developers to use the Grok for Stocks code to create derivative products that track a variety of data streams. Grok for Stocks shows how thousands of data streams can be made useful in a mobile application using HTM technology."


How Grok for Stocks Works

Grok for Stocks applies Numenta's HTM modeling and anomaly detection to 200 large capitalization public companies. It automatically models three data streams for each company: stock volume, stock price, and Twitter volume. The HTM models learn continuously, receiving new data every five minutes. HTM learns what is "normal" for each of the data streams for each company. The companies are ranked from the most anomalous to the least anomalous over the previous hour. Grok for Stocks lets you see the text of the Tweets as well, often explaining why the company is showing an anomaly.

Numenta, Inc., is a leader in the field of machine intelligence. Numenta builds technology that helps companies automatically act on streaming data. Its machine learning technology is based on a theory of the neocortex first described in co-founder Jeff Hawkins' book, On Intelligence. In addition, Numenta has created NuPIC (Numenta Platform for Intelligent Computing) as an open source project (www.numenta.org). Numenta is based in Redwood City, California.

To obtain more info about partnering and licenses, write to [email protected].


[ Back To TMCnet.com's Homepage ]