ECI's Elastic Network
  • Career
  • Follow
    • Blog
  • Login
ECI ELASTIC Network solutions logo
  • Career
  • Follow
    • Blog
  • Login
ECI-BLOG-1.jpg
ECI-BLOG-Page.jpg

The Hitchhiker’s Guide to Telco Transformation - Part 4

Posted by Amit Cohen on 28 May 2018
Amit Cohen
  • Tweet

Start Learning Machine Learning

We hear about machine learning all the time, but what is it? If we rely on Wikipedia, it looks simple. According to Wikipedia, it is a subtopic in computer science that allows machines (or computers) to learn behavior and repeat it without the need to program the operations. Within this very simple description lie a number of terms, that while simple have great implications. Such as what is learning? How does one learn or prove one has learned? But, how does it work?

First, let us look at some use cases as to better understand the value machine learning can provide:

  1. Fraud detection – used especially in by the retail industry, detects anomalies in purchasing histories by gathering and analyzing millions of data points to discover fraud patterns. This can raise alerts, detect stolen cards and avoid product shipments.
  2. Customer service – interactive chat or pop up for browsers of a website or when in need of assistance.
  3. Litigation and legal situations – models are used to translate complex legalese into layman’s terms so contracts can be better understood and negotiate. Or in court cases machine learning can help more quickly review a large amount of material so that the legal team can spent more time strategizing and less time reading and digesting hundreds of documents looking for behavioral patterns.
  4. Security – Identifying malware. Hundreds of thousands of malware are created at all the time. As humans we are limited in our ability to detect, track and deal with the thousands of alerts that are created by various tools. Machine learning helps detect, manage and identify suspicions activity.  
  5. Healthcare – Machine learning is used to learn patient medical history for better diagnosis, treatment and adjustment.
  6. Sports – Machine learning is used to better predict game results in a number of publications  

Learn More About Telco Transformation,  Download Our Elastic Services Platform Brochure

So machine learning is already being used in a wider variety of situations. There are number of types of machine learning algorithms. Two  that are most commonly discussed are:

  1. Unsupervised learning
  2. Supervised learning

Usually, one used unsupervised learning, when you don’t really know what you are looking for, nor how the data is organized. Supervised learning is used when you know what you are looking for, but would like a mathematical model to predict the future. Let’s compare the two, to better understand the differences:

Unsupervised learning Supervised learning
  • Data not clearly labeled or classified - utilizes unlabeled data, or data that has no explanations, tags, nor classifications of any kind
  • Uses “self-guided” learning algorithm – first detect data, classify the find relationships.
  • Don’t really know what you are looking for
   Example: AWS EMR with spark MLlib
  • Data clearly labeled and classified
  • Builds a predictive model
  • Use one set of data to build a model and the second set to verify accuracy of the model
  • Know what you are looking for
  • AWS 3 models:
    • Binary model
    • Multicast classification model
    • Regression model

Unsupervised learning is needed when you need to figure out the data patterns and groupings as mention the data is not labeled and no real knowledge of output and you need to figure that out, that is where unsupervised ML will be used. A common way for unsupervised ML is by deploying AWS EMR with spark MLlib.

Let’s look at supervised learning, with supervised learning we have a labeled data the data has tags or classifications and you can use that data for predictive analytics. In many cases we also know the desired output. We use this method when we have too much data to feasibly sift through. With supervised learning, the data helps the machine discover correlations between the data points and derive hypothesis about the relationship between factors.

You can compare between supervised and unsupervised learning, in the visualization below. In the case of supervised learning, the machine can see the labeled data and the correlation between the elements and use these to help make a prediction about the other data points.  With unsupervised learning there are no labels, you cannot see the relationships and you need to figure out what is in the data and what is it that you looking at.

Machine-Learning-1

The components of machine learning include:

  1. Data source – Any DB info or CSV file extracted from big data system.
  2. Split Data – The data is split into 2 groups: training data and evaluation data. Training data is used by the algorithm to learn predictive relationships between the various pieces of data. Evaluation data is then used to verify the accuracy of the model.
  3. Shuffle Data – Shuffling data is important because it helps to improve the quality of the ML model. Since the data used in training influences the algorithm or prediction, shuffling the data between the sets and comparing can lead to a better, more accurate model. Shuffling the data places it in a random order, AWS ML created better models when the data is in random order.
  4. Data Transformation – the ML helps optimize the data for better learning. This can then be used to classify new information and can help with future learning.
  5. Training Model – Once data transformation is concluded, it is time to create a model and train that model, by finding patterns and correlations in your data. This is where we are teaching the ML algorithm to hypothesize and make predictions based on the data.
  6. Model Parameters – Customize your model, for example, you may want to increase the amount of data or add parameters to it.
  7. Evaluation Model – Determine accuracy or quality of the model in predicting instances not in the training data. There are several ways to validate you models such as: model insights, binary model insights, multiclass model insights, regression model insights, preventing overfitting, cross-validation, evaluation alert, etc…
  8. Feature Selection – Adjust learning/model size, you may even drop features that do not contribute to the learning process.
  9. Score Setting – Score for prediction accuracy.

Use Model - get the predictions in: Real-Time or batch. Real time is used in web apps or mobile apps. Batch predictions send us data as a CSV file.

Start-Learning-Machine-Learning

The post is a short extraction of what is ML its use cases and what are the process steps been used from getting the data until getting the insights out of it.

It is the first one in a series of ML posts where I will go deeper in the process and the components of it.

Stay tuned…

Learn More About Telco Transformation,  Download Our Elastic Services Platform Brochure

lipr_14.png

Topics: Service Providers, 5G, Telco Transformation

Subscribe to ECI Email Updates

aboutheauthor-new
Amit Cohen
Amit Cohen

Senior Director, Cloud Platforms Chief Principal Architect, NFV/5G/IOT at ECI. Amit has a track record of technical & business roles in management & leadership, product management & innovation, sales management and business development in IT and Telecommunication industry within international software vendors: Novell, Microsoft, Alcatel-Lucent & Huawei. Amit is responsible for end to end NFV & SDN system design & architecture at ECI R&D.

ECI For Network Solutions
brows-categories-new

  • SDN (57)
  • Service Providers (57)
  • Optical Networking (39)
  • 5G (38)
  • NFV (34)
  • Critical Infrastructures (32)
  • Cyber Security (28)
  • Utility (27)
  • Network Modernization (23)
  • Packet Networking (18)
  • IP (16)
  • Mobile Backhaul (15)
  • Cloud Networking (13)
  • Enhancing Network Efficiency (13)
  • Other (12)
  • Carrier Ethernet (11)
  • Network Slicing (11)
  • Telco Transformation (11)
  • Africa (9)
  • IoT (9)
  • Legacy Networks (8)
  • SD-WAN (8)
  • telecom (8)
  • Open Source (7)
  • Segment Routing (7)
  • Software (7)
  • containers (7)
  • Multi-Layer Optimization (6)
  • Packet (6)
  • Smart Grid (6)
  • Aligning Network Architectures (5)
  • Disaggregation (5)
  • FlexE (5)
  • Intelligent Networking (5)
  • Metro (5)
  • Network Management (5)
  • Network Transformation (5)
  • Open (5)
  • Optical Networks (5)
  • Sustainability (5)
  • general (5)
  • Access (4)
  • Hardware (4)
  • MEC (4)
  • Network Operations (4)
  • OTT (4)
  • Orchestration (4)
  • Smart City (4)
  • Telecoms (4)
  • UTelco (4)
  • Utilities (4)
  • VMs (4)
  • Artificial Intelligence (3)
  • Cloud Design (3)
  • DER (3)
  • Digital Transformation (3)
  • Environment (3)
  • Ethernet (3)
  • FTTH (3)
  • FlexibleEthernet (3)
  • Logical Network (3)
  • MPLS (3)
  • Multi-Tenant (3)
  • Network Automation (3)
  • PaaS (3)
  • Software Defined Networks (3)
  • Virtualization (3)
  • WAN (3)
  • eMBB (3)
  • 5G business case (2)
  • APIs (2)
  • Big-Data (2)
  • Broadcast (2)
  • Business Services (2)
  • DWDM (2)
  • Data Center Interconnect (2)
  • DevOps (2)
  • Distributed Energy Resources (2)
  • Encryption (2)
  • IP/MPLS (2)
  • India (2)
  • Interoperability (2)
  • Latency (2)
  • MEF (2)
  • Machine Learning (2)
  • Mobile (2)
  • Multi-Access Edge Computing (2)
  • NFVi (2)
  • Network Design (2)
  • OTN (2)
  • Open Optical Systems (2)
  • OpenFlow (2)
  • Optical Encryption (2)
  • PCE (2)
  • Telecommunications (2)
  • VIM (2)
  • hyperscale (2)
  • microservices (2)
  • uCPE (2)
  • 5G Network Evolution (1)
  • 5G ROI (1)
  • 5G spectrum (1)
  • API economy (1)
  • AR/VR (1)
  • ATM (1)
  • Airports (1)
  • Autonomous Vehicles (1)
  • Bandwidth (1)
  • Bandwidth on Demand (1)
  • Bitcoin (1)
  • Blockchain (1)
  • Branch Office (1)
  • Business Care (1)
  • CLNS (1)
  • CMTC (1)
  • Capacity (1)
  • Carriers (1)
  • Cloud Service Providers (1)
  • Coherent Transport (1)
  • Complete Network Environment (1)
  • Connected Cars (1)
  • Core (1)
  • Core Transport (1)
  • Dedicated ASIC (1)
  • Dockers (1)
  • Drones (1)
  • ESP (1)
  • EV (1)
  • Electric Vehicles (1)
  • FDDI (1)
  • Firewalls (1)
  • Future Proof (1)
  • God Box (1)
  • ICT (1)
  • IEEE (1)
  • IP Technologies (1)
  • IPoverDWDM (1)
  • IPv6 (1)
  • IaaS (1)
  • Industry 4.0 (1)
  • Intent-based Networking (1)
  • LAN (1)
  • Layer 1 Encryption (1)
  • Legacy Technology Migration (1)
  • Lifecycle Management (1)
  • Local Area Network (1)
  • Low Latency (1)
  • MMTC (1)
  • MPLS-TP (1)
  • Massive Machine Type Communications (1)
  • Metro Aggregation (1)
  • Mobile Edge Computing (1)
  • Municipalities (1)
  • NOS (1)
  • Network Migration (1)
  • Network Operating Systems (1)
  • Network Planning (1)
  • Network Security (1)
  • Network Upgrade (1)
  • Non-coherent (1)
  • Novell Netware (1)
  • OLS (1)
  • OSI Stack (1)
  • Open Architectures (1)
  • Open Optics (1)
  • Packet Migration (1)
  • Packet-Optical (1)
  • Power (1)
  • Pricing (1)
  • RESTful (1)
  • Railway (1)
  • Research and Education (1)
  • Routing (1)
  • SCADA Anomaly Detection (1)
  • SONET (1)
  • Security (1)
  • Self-Organizing Networks (1)
  • Shannon Limit (1)
  • Smart Transportation (1)
  • Stateful (1)
  • Stateless (1)
  • Token Ring (1)
  • Transformation (1)
  • Transportation (1)
  • Transportation Systems (1)
  • URLL (1)
  • URLLC (1)
  • VNFs (1)
  • VPN (1)
  • Vendor Agnostic (1)
  • Whitebox (1)
  • e-learning (1)
  • eVPN (1)
  • enterprise (1)
  • hyperconvergence (1)
  • lightPULSE (1)
  • vCPE (1)
see all
archive-new

  • January 2019 (7)
  • December 2018 (3)
  • November 2018 (8)
  • October 2018 (8)
  • September 2018 (6)
  • August 2018 (4)
  • July 2018 (8)
  • June 2018 (7)
  • May 2018 (8)
  • April 2018 (8)
  • March 2018 (8)
  • February 2018 (7)
  • January 2018 (6)
  • December 2017 (4)
  • November 2017 (7)
  • October 2017 (8)
  • September 2017 (7)
  • August 2017 (4)
  • July 2017 (8)
  • June 2017 (8)
  • May 2017 (8)
  • April 2017 (6)
  • March 2017 (7)
  • February 2017 (7)
  • January 2017 (5)
  • December 2016 (3)
  • November 2016 (7)
  • October 2016 (5)
  • September 2016 (6)
  • August 2016 (6)
  • July 2016 (6)
  • June 2016 (6)
  • May 2016 (7)
  • April 2016 (9)
  • March 2016 (8)
  • February 2016 (7)
  • January 2016 (5)
  • November 2015 (6)
  • October 2015 (1)
  • April 2015 (1)
  • March 2015 (1)
  • January 2015 (1)
  • December 2014 (1)
  • October 2014 (1)
  • August 2014 (1)
  • July 2014 (1)
  • January 2014 (1)
  • December 2013 (2)
  • December 2012 (1)
  • July 2012 (1)
  • June 2012 (1)
  • May 2012 (2)
  • March 2012 (2)
  • February 2012 (3)
  • January 2012 (2)
  • December 2011 (2)
  • November 2011 (5)
  • October 2011 (4)
  • September 2011 (5)
  • April 2011 (5)
  • February 2011 (2)
  • January 2011 (4)
  • December 2010 (5)
  • November 2010 (6)
  • October 2010 (4)
  • September 2010 (4)
  • August 2010 (6)
  • July 2010 (8)
See All

Recent Posts

Industries

  • Service Providers
  • Utilities and Strategic Industries
  • Data Center
  • Research and Education Network

Products

  • Elastic Services Platform
  • Transport Product Lines
  • Management
  • Muse™ - Network and Service Applications
  • Muse™ - Cyber Security Suite
  • Mercury™ - NFV Solutions

Services

  • Professional Services
  • Services Login

Partners

  • Partner Program
  • Partner Login

RESOURCES

  • What's Hot
  • What's New
  • In the News
  • Blogs
  • Events
  • Webinars
  • Innovation

About

  • Exec Team
  • Global Offices
  • Association
  • Corporate Responsibility
  • Contact
  • We're Hiring!
  • Privacy
  • Terms
© All rights reserved ECI Telecom 2018