NetOwl

NetOwl offers best-of-breed, multilingual entity extraction from text. It offers a broad semantic ontology and extracts not only named entities but also links and events with state-of-the-art accuracy. It is scalable and ideal for Big Data Analysis of unstructured data.

NetOwl goes beyond simple positive vs. negative sentiments offering entity-based sentiment analysis. It captures what exactly people like or do not like and provides deep insights into their opinions, attitudes, intentions, and behaviors.

NetOwl’s award-winning, machine learning-based matching technology offers accurate, fast, cross-lingual name matching. It is used in such applications as anti-money laundering (AML), regulatory compliance (KYC, PEP), border security, and counterterrorism.

NetOwl performs fast and scalable machine learning-based identity resolution, combining evidence from not only names but also other key entity attributes such as date of birth, nationality, address, phone number, and employer.

Financial firms must ensure that they are compliant with applicable laws and regulations focused on the prevention of money laundering (AML) and terrorist financing (KYC, PEP), among others. NetOwl’s name matching and identity resolution products help verify that customers are not on any sanction lists, such as the Specially Designated Nationals list from the Office of Foreign Assets Control (OFAC), and therefore that they are not money launderers, terrorists, or fraudsters.

With vast amounts of news and other media available, it is now possible to monitor and identify negative information concerning organizations and people in a more timely and comprehensive way as part of AML, KYC, and general due diligence efforts. NetOwl’s advanced entity, relationship, and event extraction detects a variety of adverse events involving companies and people in real time with high accuracy.

Robust border security requires accurate and fast matching of names against a variety of watch lists. Watch lists often contain names from different ethnicities and cultural backgrounds, which pose a variety of challenges, including transliteration variants, name order variations, orthographic differences, etc. NetOwl’s award-winning, empirically driven, machine learning-based approach provides highly accurate, fast, and scalable automated name matching.

Intelligence analysts must analyze staggering amounts of data from multiple sources in multiple languages to identify critical information and discover hidden links. NetOwl text analytics software turns unstructured data into structured information that can be easily searched, visualized, and exploited by other analytical tools. NetOwl’s advanced entity extraction supports semantic search and link analysis while geotagging enables geospatial analysis of text.