Simplifying Field Operations Using Machine Learning (2017)

By Sanjay Dorairaj, Bernard Burg & Nicholas Pinckernell, Comcast Corporation; Chris Bastian, SCTE

Every so often in the history of our evolution, humans discover something so important that it propels usinto a new plane of technological and intellectual superiority. Over two million years ago, the Stone Age helped us build tools that established us as the dominant species on this planet. Much later, the Bronze Age (circa 3500 BC) and the Iron Age (circa 1200 BC) catapulted us to new levels of technological sophistication through the introduction of coin-based currencies, faster means of transport, durable manufacturing and construction and numerous other developments. This laid the foundation for the Industrial Age (circa 1700 AD), which ushered in the age of mechanized agriculture, mass transportation and electronic communication. The invention of the computer and the internet in the later parts of the 20th century heralded the dawn of the Internet Age. Individuals anywhere on the globe could now communicate and exchange information with one another. And much like Ray Kurzweil’s Law of Accelerating Returns[1], the Internet Age is hardly over. Now, we find ourselves at the cusp of two back to back, tightly coupled events that are also bound to be of equally great historical significance - the Age of Big Data and the Age of Machine Learning.

The explosion in data aka “Big Data”, is a direct result of the exponential improvements in computing power and storage, with similar decreases in their cost [2]. This fueled an abundance of both personal and organizational data. The chart, below, provides a dramatic portrayal of the rapid growth of data over just one decade. Despite all of this data, the insights that we were able to generate has been limited by decades old statistical and mathematical techniques and there wasn’t much innovation in this field. The advent of Machine Learning has propelled us forward, by offering techniques that transform the big data into a veritable gold mine of valuable insights.

This paper is about machine learning - its definition and its applications. It especially examines the relevance of machine learning from the perspective of the cable’s multiple system operators (MSOs). While there have been some attempts in technical and trade literature to pinpoint the benefits of machine learning to cable service operators, there has not yet been a holistic treatment of the subject, to our knowledge. This paper is an attempt to fill that gap.

By clicking the "Download Paper" button, you are agreeing to our terms and conditions.

Similar Papers

Predicting Service Impairments from Set-top Box Errors in Near Real-Time and What to Do About It
By Justin Watson, Comcast; Roger Brooks, Andrew Colby, Pankaj Kumar, Anant Malhotra & Mudit Jain, Guavus, Inc.
Using AI to Improve the Customer Experience: A Virtual Assistant Chatbot
By Bernard Burg, Fan Liu, Abel Villca Roque, Sunil Srinivasa, Ryan March & Tianwen Chen, Comcast
A PNM System Using Artificial Intelligence, HFC Network Impairment, Atmospheric and Weather Data to Predict HFC Network Degradation and Avert Customer Impact
By Larry Wolcott, Michael O'Dell, Peter Kuykendall, Vishnu Gopal, Jason Woodrich & Nick Pinckernell, Comcast
Operationalizing Streaming Telemetry and Machine Learning Model Serving: Customer Experience Automation
By Nick Pinckernell & Scott Rome, Comcast
Embracing Service Delivery Changes with Machine Learning
By Andrew Sundelin, Guavus, Inc.
Machine Learning: The Past, Present and the Future
By Narayan Srinivasa, Intel Corporation
A Machine Learning Pipeline for D3.1 Profile Management
By Maher Harb, Jude Ferreira, Dan Rice, Bryan Santangelo & Rick Spanbauer, Comcast
Machine Learning Techniques for Equalizing Nonlinear Distortion
By Rob Thompson, Comcast; Xiaohua Li, State University of New York at Binghamton
Toward Automated Intelligent Resource Optimization for vCMTS Using Machine Learning
By Kieran Mulqueen, Michael O’Hanlon, Marcin Spoczynski, Brendan Ryan, Thijs Metsch, Leonard Feehan & Ruth Quinn, Intel
Applications of Machine Learning in Cable Access Networks
By Karthik Sundaresan, Nicolas Metts, Greg White, Albert Cabellos-Aparicio, CableLabs
More Results >>