Data Classification

Operational Automation AI improves Quality and Consistency of Operational Decisions with Machine Guided Outcomes. Get instant insight into threats and opportunities without the need for ETL or a complex specialized data store.

Classification and clustering are examples of the more general problem of pattern recognition, which is the assignment of some sort of output value to a given input value. Other examples are regression, which assigns a real-valued output to each input; sequence labeling, which assigns a class to each member of a sequence of values (for example, part of speech tagging, which assigns a part of speech to each word in an input sentence); parsing, which assigns a parse tree to an input sentence, describing the syntactic structure of the sentence; etc. A common subclass of classification is probabilistic classification. Algorithms of this nature use statistical inference to find the best class for a given instance. Unlike other algorithms, which simply output a "best" class, probabilistic algorithms output a probability of the instance being a member of each of the possible classes. The best class is normally then selected as the one with the highest probability. However, such an algorithm has numerous advantages over non-probabilistic classifiers:



What Problem Does This Solve?
Data is at the heart of the machine learning race. It lives in files, databases, cloud and web apps as a constantly changing stream of information that can be analyzed and turned into Knowledge and Insight.

Get things done faster with a powerful multi-model data store. Application Dataspaces™ let you store massive amounts of data as tables, documents, key-value, queues or columnar store. In-memory computing and data compression make it ideal for Data Science and Probabilistic Analysis.
Classifying Documents + Text
Use Reactive Programming to turn anything into a Data Stream. Triggers, Actors and Event Collections make it easy to build data pipelines and work with high-velocity data using simple SQL-like syntax.

Capture changes from File Storage, Database or IoT devices and transform them into meaningful events that power Cognitive AI applications for real-time decision making.
Thematic Analysis
If you can describe it, we can query it. Know SQL and Javascript? Then you already know how to use the platform. Whatever the format, a powerful query language lets you work with structured or unstructured data, speeding up development and simplifying deployment for unmatched data agility.

A rich Data Virtualization layer links file systems, Web servers, relational databases, No-SQL and Big Data storage; allowing them to be queried and joined to any other data. Virtual collections let you integrate data from any source and easily load it into memory for fast processing and analysis.
Topic Modeling + Key Phrases
We know you're busy. The data fabric is purpose-built to reduce the burden on support teams. Cognitive Technology features for AI Ops let you automate administrative tasks and engage teams globally to solve problems, reduce down time and accelerate problem resolution.

Collect and store critical metrics to monitor operations in real-time. Define Triggers and Task Lists, that react to KPI changes, application data, CPU, memory usage, and resource availability. Log and machine data can be automatically classified, analyzed for context or relevance and easily integrated into Call Center applications to automate support decisions.
Synonymy, Hypernymy or Similarity
StreamScape's cognitive technology makes use of Natural Language Processing and Classification to discover meaning and context in data by analyzing language and sentence structure. Microflows and Data Integration services make it easy to import data and automate model training.

Thematic Analysis services let users easily collect and analyze text, document, image or audio data to understand concepts, opinions, or experiences and gain deeper insight into problems. This type of analysis is considered interpretative, as it is shaped and informed by domain specific knowledge, concepts and terminologies.
Feature Engineering
Enterprise grade, integrated security keeps your data safe. Entity or column-level Authorization, Group, Organization and API security protects critical information against unwanted access and data co-mingling.

Expose functions, queries and AI services as fully documented API, powered by the industry's leading Open API framework. Develop Real-Time, AI powered applications that integrate documents, web or application data from any source.

Connect to the platform using any language, Web application, OData compliant systems, XMPP or JDBC clients, Microsoft Office products, Reporting and Data Visualization tools.
Download a full version of the
Data Fabric