Lumina Expands Its Predictive Analytics and Risk Sensing Capabilities with Radiance(SM) Launch

Ai-Powered Technology Helps Organizations Anticipate, Understand, Manage and Mitigate Risk

Lumina announced the launch of its new Radiance platform, which uses proprietary, deep-web listening algorithms to uncover risk, provide timely and actionable information and help prevent catastrophic loss. The Radiance platform brings the power of Open-Source Intelligence (OS-INT), Internet Intelligence (NET-INT) and the See Something Say Something app (HUM-INT) for edge-to-edge risk detection.

“The power of Radiance is two-fold – its ability to ingest massive amounts of unstructured, open source data and its real-time ability to analyze that information to predict and prevent organizational risks and threats,” said Allan Martin, CEO of Lumina. “Radiance is designed to help keep people and places safe and secure, and this AI-driven solution will immediately transform how organizations think about risk management and risk mitigation.”

Read More: Aptiv/Audi Receives Innovation Partnership Award for Automated Driving Satellite Compute Platform

Radiance’s purpose-built, best-in-class algorithms overcome the challenges of massive unstructured data ingestion and prioritization.  Radiance scours the web, prioritizing current behaviors to predict future action.  This is an advantage over other technologies, which focus only on historical behavior, which can lead to bias in the results. Additionally, clients can integrate their own structured and unstructured data into Radiance, allowing for correlation of internal databases against open source, publicly available data.

Radiance is a Software-as-a-Service (Saas) platform that includes managed service capabilities. It is rapidly deployable, scalable, highly configurable and user-friendly, and is comprised of the following components:

• Radiance Open Source Intelligence (OS-INT) is a deep-web listening tool that uses machine learning and artificial intelligence to assess and prioritize risk. Names entered into OS-INT are correlated with content related to 20 different risk factors, known as Behavioral Risk Profiles (BRPs) and cross-referenced with more than 1 million queries into Lumina’s proprietary databases of risk, known as ecosystems. One search across all BRPs equates to more than 465,000 deep web searches. OS-INT delivers prioritized results in about 5 minutes. A manual search of this magnitude would take a person more than 3 1/2 years to complete.
• Radiance Internet Intelligence (NET-INT) detects means, motivation and target for attack planning. Its proprietary algorithms continuously identify, monitor, capture and prioritize IP addresses exhibiting anomalous behavior across multiple risk dimensions. The platform collects and stores more than 1 million interactions every day and since its inception has recorded more than 623,000 IP addresses engaged with threat-related risk topics.
• Radiance Human Intelligence (HUM-INT) is powered by the S4 app, a crowd-sourced, mobile application that allows users to confidentially report concerns in real time. A centralized management portal allows clients to access real-time threats to geo-fenced locations.

Read More: Fly like a Hero with the Brand New Tello Iron Man Edition

“We constantly hear people say, ‘We have so much data, but what can we do with it?’  Radiance solves that problem by ingesting, integrating, correlating and analyzing disparate datasets.  It takes data never designed to identify risk, and prioritizes it – giving our clients an unbiased and fully auditable understanding of human behavior and associated threats,” said Dr. Morten Middelfart, Chief Data Scientist at Lumina.

He added that Radiance’s BRPs solve for the “data noise” obstacle associated with other OS-INT SaaS solutions.  In addition, Radiance drastically outperform existing Natural Language Processing (NLP) approaches to identify names of persons or entities in unstructured data. Radiance performed at a 93.1 percent accuracy level on unstructured, improperly cased documents such as HTML, JSON or computer code and other so-called messy documents compared to 0 percent for Stanford Named Entity Recognizer (NER) and other popular open-source NLP software. Additionally, the BRPs generated with Lumina’s machine learning are “human readable,” making them fully auditable as well.

Read More: World’s Largest Business Organization Partners with Perlin for Blockchain Adoption Across Its 45 Million Members