Architecture

Enterprises are experiencing the need to move to new architectural approaches so they can harness the value of big data and adapt to the evolution of data in terms of:

  • Volume – 90% of today’s data has been created in the last two years
  • Velocity – Globally, internet traffic will achieve a rate of 50,000GB/s by 2018
  • Variety – 90% of generated data is unstructured

To successfully adapt to these fundamental changes and achieve the goal of real-time access to and analysis of massive volumes of data as it traverses networks at unprecedented speeds, a shift in approach is needed:

  • A shift from proprietary architectures to Hadoop
  • A shift from data silos to a data lake
  • A shift from rules to rules and machine learning
  • A shift from batch to real-time predictive analytics

This requires a deep understanding of the following three areas:

The Data Lake:
A 360o Perspective

One of the biggest issues facing enterprises and communications service providers is that all their data is dispersed in separate silos or islands – including billing and usage info across hundreds of billing systems, customer data, CRM and care systems, ordering, inventory and supply chain systems as well as data from other enterprise and legacy areas. To undertake meaningful analysis the data must be combined. This requires the creation of an enterprise data hub, or data lake, which can store unlimited amounts of data, cost-effectively and securely, from which data can be processed, explored, modeled, and served in one unified platform

To do this effectively requires integrating many types of data into a data lake.

Batch Billing Data
TD.35, CDR, TAP 3

Real-Time Call Packets
ISUP, BSSAP, MAP

Real-Time Fixed Call Packets
ISUP, Diameter

Real-Time VoIP Call Packets
SIP, H.323, Diameter

Real-Time Data Packets
GTP, Diameter

Business Data
CRM, Billing

Machine Learning

Machine learning, the science of getting computers to learn from data and act without being explicitly programmed, is key to unlocking the value of big data. Using an enterprise data hub, or data lake, it is possible to use machine learning for predictive network analytics in real time, uncovering traffic patterns, validating subscribers, discovering fraud, or implementing IoT security in ways not previously possible. Sophisticated multi-domain machine learning analytics offers unprecedented visibility into the characteristics of data traffic and user behaviors for enterprises and communications service providers.

Argyle Data’s world-leading data scientists have developed unique approaches using the latest research in machine learning to deliver predictive analytics in real time.

Real-Time Feature Enrichment
As entries are stored, features are created in real-time

Real-Time Anomaly Detection
As entries are stored, anomalies are detected by looking at the new entry and a historic pattern in real time

Real-Time Fraud Alerts
As fraud is detected, revenue threat alerts are sent to the analyst dashboard

Big Data Native Hadoop Architecture

Hadoop’s standard-based open-source framework leverages the power of massive parallel processing to take advantage of big data using lots of inexpensive commodity servers. The new generation of big data/machine learning applications must be entirely built on the new platform. They will be written by masters of writing applications in new ways using native (BigTable type) Hadoop distributed key/value stores, native Hadoop distributed SQL, and machine learning operating against native Hadoop stores with powerful graph analytics.

Argyle Data’s approach delivers the ingestion rates of a key-value/triple store and the querying power of a distributed SQL database, natively on Hadoop.

Performance
Interactive response times at petabyte scale, in parallel across hundreds of nodes

Full Secondary Indexing
Interactive response times at petabyte scale on primary and secondary indexes

ANSI SQL
Powerful queries and standard integrations to visualization frameworks

Request a Demo

Get Our E-Book