Artificial Intelligence capabilities in Siren 10.3 release

Siren, an investigative intelligence platform released Siren 10.3. The latest version of Siren launches five new artificial intelligence (AI) capabilities: entity resolution, deep learning-based predictive analytics and alerting, deep learning-based times series anomaly detection, real-time topic clustering for textual corpuses and associative model technology for dashboards (“Dashboards 360”).

The new AI enhancements introduced in 10.3 can be used immediately in big data use cases such as fraud and crime investigation (financial, law enforcement), operational analytics (ITOps, cybersecurity, SIEM, telecommunications, IoT), and data discovery (knowledge graph/enterprise knowledge exploration and search).

“AI is the core of modern augmented analytics and with Siren 10.3 we introduce new AI functionality following intensive research and development. This is a major step forward not just for our platform but for the industry in general as augmented analytics is now a reality on a big data scale. The package of AI capabilities we have launched will provide users with a rich, visual experience resulting in data becoming more meaningful and readily accessible,” said Dr. Giovanni Tummarello, Co-Founder and Chief Product Officer at Siren.

10.3 offers the following AI capabilities:

State of the art self-correcting Entity Resolution, this is the AI/ML ability to recognize that records across different tables and data sources, using different schemas and different languages, are in fact talking about the same entity (person, company). Siren ER is real-time and capable of “self-correcting” previous statements as new information arrives.

Deep learning-based predictive analytics and alerting real-time forecasting of operational data streams and alerting on the expected future crossing of set thresholds.

Deep learning-based time series anomaly detection, the capability of learning from data to recognize and alert for anomalous behavior. Unlike other offerings on the market, Siren offers this based on automatic model selection ML, powered by dockerized TensorFlow backed APIs with seamless front-end integration.

Real-time topic clustering for textual corpuses, for documents which have text (reports, emails, news articles, etc.), Siren now provides a built-in real-time visual interactive clustering exploration UI which is a critical capability for news monitoring, investigative textual data discovery, and e-discovery.

Associative Relational Technology, called “Dashboard 360”, this is the ability to see in a single view a full “associative model” 360-degree picture. This feature was previously only available in high-end BI systems which required all of the data to be loaded in memory and was therefore not applicable to operational tasks, for example, those that require Elasticsearch. This provides an unprecedented ability to visualize and interactively investigate in a single dashboard. 

In addition to the introduction of the five AI capabilities, 10.3 also includes the following notable enhancements:

• Siren’s built-in visual knowledge graph exploration now works with intuitive drag and drop operations from/to dashboards.
• New connector to local or to multiple remote Elasticsearch Clusters, regardless of version.
• Visual wizard for Neo4J connectivity makes Neo4J data exploration more straightforward.
• High performance, patent-pending caching strategy (Irish Application No S2019/0126) is now enabled on the Siren Elasticsearch plugin (the Siren Federate technology).
• The Siren platform is now easier to configure and maintain with improved configuration objects granularity and configuration setup.

“Augmented analytics” is a term coined by Gartner to define the next wave of analytics, where AI and analytics techniques work seamlessly together to provide additional value to data scientists. Gartner expects that, in the next few years, citizen data science will rapidly become more prevalent as an approach for enabling and scaling data science capabilities more pervasively throughout the organization. Gartner predicts that, by 2020, due in large part to the automation of data science tasks, citizen data scientists will surpass data scientists in the amount of advanced analysis produced. Gartner predicts that, by 2020, more than 40% of data science tasks will be automated, resulting in increased productivity and broader use by citizen data scientists.