SlideShare une entreprise Scribd logo
1  sur  31
Télécharger pour lire hors ligne
background image: 960x540 pixels - send to back of slide and set to 80% transparency
Advanced Analytics for
Telecommunications
Bob Glithero, Principal Product Marketing Manager
Vineet Goel, Product Manager
background image: 960x540 pixels - send to back of slide and set to 80% transparency
Agenda
•  Pivotal – Hortonworks Partnership
•  Challenges in Customer Experience
•  HDB: Hadoop-Native Analytics Database
for Hortonworks Data Platform
•  Sample Use Cases
•  For More Information
Pivotal HDB + Hortonworks Hadoop
Partnering for Faster Value from Data
●  Leaders in open-source Hadoop
●  Managing, analyzing, and operationalizing data at
scale
●  Joint support for ODPi promotes interoperability in
Hadoop
+
Pivotal and Hortonworks’ strategic partnership marries
Pivotal’s best-in-class SQL on Hadoop, analytical
database, with Hortonworks’ best-in class expertise and
support for Hadoop.
You’re the third
person I’ve
been handed
off to!
Can’t anyone
help me?
4
I’m not
seeing any
alarms...why
are our
customers
having poor
service?
5
Managing Experience is Complicated
Then
•  Basic handsets, embedded applications
•  Simpler services - voice, SMS, WAP
•  Experience influenced mostly inside the network
Now
•  From phones to hand-held computers
•  Massive data volume, velocity, and variety from millions of apps and
services
•  MNOs held responsible for all aspects of service, whether inside or
outside the network
CSPs Increasingly Competing on QoE
Trying to understand how network
performance impacts experience
When service is degraded, CSPs need
to quickly understand:
Is the problem inside or outside the
network?
Which subscribers are impacted?
What needs attention first?
Common Operator Challenges
Network Operations Customer Care Marketing
Increase monetization, offset
voice, SMS revenue loss
Reduce churn and
credits, cost to serve
Reduce complexity,
increase visibility,
increase QoE
background image: 960x540 pixels - send to back of slide and set to 80% transparency
Operators are turning to their data to
solve these challenges
How do we analyze data in an
efficient, cost-effective way to
transform customer experience?
High performance, interactive SQL queries on Hadoop
HDB: The Hadoop Native SQL Database
●  Highly efficient MPP
(massively parallel processing)
●  Low-latency
●  Petabyte scalability
●  ACID transaction support
●  SQL-92, 99, 2003 compatibility
●  Advanced cost-based optimizer
DATA LAKE
SQL App
BUSINESS ANALYSTS
DATA SCIENTISTS
Advanced Analytics
Performance
Exceptional MPP performance, low
latency, petabyte scalability, ACID
reliability, fault tolerance
Most Complete
Language Compliance
Higher degree of SQL compatibility,
SQL-92, 99, 2003, OLAP, leverage
existing SQL skills
Best-in-class Query
Optimizer
Maximize performance and
do advanced queries with confidence
Elastic Architecture for
Scalability
Scale-up/down or scale-in/out, expand/
shrink clusters on the fly
Tightly integrated w/
MADlib Machine
Learning
Advanced MPP analytics, data science at
scale, directly on Hadoop data
HDB / HAWQ Advantages
MAD
●  Discover	New	Rela/onships	
●  Enable	Data	Science		
●  Analyze	External	Sources	
●  Query	All	Data	Types!	
Mul/-level	
Fault	Tolerance	
Granular	
Authoriza/on	
Resource	Pools	
+	YARN		
Mul$-tenancy	+	Security	
ANSI	SQL	
Standard	
OLAP	
Extensions	
JDBC	ODBC	
Connec/vity	
MPP	
Architecture	
Online	
Expansion	
Hadoop	/	HDFS	
Petabyte	Scale		
Cost-Based	OpXYZizer	
Dynamic	
Pipelining	
ACID	+	
Transac/onal	
Ambari	
Management	
Machine	
Learning	
Data	
Federa/on	
Language	
Extensions	
Hardened,	10+	Years	Tested,	Produc/on	Proven	
Opera$ons	+	Extensibility	
HDFS	Na/ve	
File	Formats	
●  Manage	Mul/ple	Workloads	
●  Petabyte	Scale	Analy/cs	
●  Sub-second	Performance		
●  Leverage	Exis/ng	
Skills	&	Tools	
●  Easily	Integrate	with	
Other	Tools	
	
	
Compression	
+	Par//oning	
Core	
compliance	
●  Well	Integrated	with	
Hortonworks	Data	
PlaZorm	
	
	
HDB + HDP Marketecture
13
Faster Insight with In-Database Analytics
Pivotal HDB /
Apache HAWQ (incubating)
Low-latency, MPP analytic
database with full ANSI SQL
support running natively on
Hortonworks HDP
Apache MADlib (incubating)
Scale out, SQL-based
machine learning within
HDB/HAWQ, Greenplum, and
PostgreSQL databases
+
14
Top MADlib Use Cases
•  Fraud detection
•  Risk analysis
•  Customer experience
•  Marketing
•  Predictive maintenance
Telco uses HDB to analyze and improve call quality
2bn call records per day
•  Overwhelmed traditional data warehouse
Hadoop and HDB
•  5x data stored at half the cost
•  Familiar SQL interface to analyze 3 months
worth of dropped call data
DATA LAKE
16
How could a network operations team apply analytics to
improve experience for its network services?
What Data Is Needed?
Service Assurance Customer Care Marketing
• Network Performance data (GTP
probe data)
• HTTP Click Stream Records
• Flow Records
• Network & Device Reference
Data
• Topology and location
• HTTP Click Stream Records
• Flow Records
• Network Performance data (GTP
probe data)
• CRM data (account, device
information)
• Service Request Records
• HTTP Click Stream Records
• Flow Records
• CRM data (account, device
information)
Constructing KQIs from performance indicators
84%
Speed
Latency
Effective
Throughput
Integrity
Drops
Time-Outs
Cut-Offs
Failures
Retainability
Failure %
Response time
Access time
Accessibility Voice QoE
Data capture Data science
•  xDRs
•  NetFlow
•  Probes
Data processing
Accessibility
Quality
Retainability
In-Database Analytics with HDB and MADlib
Application/
Content Data
•  Raw Usage
•  Logs
•  (HTTP, Flow, Other)
HDFS
HBase
Hive
HDB/HAWQ
In-DB AnalyticsNetwork Data
•  Probes (GTP-C/U)
•  xDRs
•  Case management
•  CRM
•  Billing
•  Device inventory
•  Network topology
•  Geolocation maps
B/OSS Data
PXF
PXF
MPP Query Execution
ANSI SQL
•  SQL-based
•  Over 50 data science
functions
•  UDFs
•  Offline modeling
•  Batch queries
•  Reporting/viz with
SQL-based tools
+
Native or PXF
20
How could marketing teams use
analytics to better target
subscribers for promotions and
advertising?
Blended Mobile ARPU is Declining
Loss of voice and SMS
ARPU from competition,
free apps
Data revenues not
offsetting voice, SMS
losses
MNOs seeking new
monetization options
Source: IHS Technology Mobile ARPU Forecast, 2016
Need for Behavioral Insights
•  CSPs need to maximize subscriber
yields to offset declining revenues
•  Marketers have little information to
market to anonymous prepaid
subscribers
•  Need to protect current revenue
from competition from over-the-top
(OTT) apps and services
Morning: New York
•  Starts on Samsung Galaxy S6
•  On CNN, sees news on earthquake
•  Donates via Red Cross Society
•  Later: Switches to iPad – same account
plan
•  Checks market close on WSJ.com
A Day in the Life: User Perspective
Evening: Boston
•  Checks Facebook page
•  Streams Netflix
SubscriberId	 StartTimeStamp	 EndTimeStamp	 URL	 User Agent	
RK2FQ9PWZVW52	 2015 04 28 06 37 04 512	 2015 04 28 06 37 04 543	http://www.cnn.com	 Mozilla/5.0 (Linux; U; Android 4.4.2; en-US; SAMSUNG-SM-N900A Build/KOT49H) CNN/2.1.1 	
RK2FQ9PWZVW52	 2015 04 28 06 37 05 546	 2015 04 28 06 37 04 623	http://www.cnn.com/world	 Mozilla/5.0 (Linux; U; Android 4.4.2; en-US; SAMSUNG-SM-N900A Build/KOT49H) CNN/2.1.1 	
RK2FQ9PWZVW52	 2015 04 28 06 37 19 529	 2015 04 28 06 37 19 599	
http://www.cnn.com/2015/04/28/asia/flight-delhi-
nepal-earthquake/index.html	 Mozilla/5.0 (Linux; U; Android 4.4.2; en-US; SAMSUNG-SM-N900A Build/KOT49H) CNN/2.1.1	
RK2FQ9PWZVW52	 2015 04 28 06 37 23710	 2015 04 28 06 37 23 770	http://www.cnn.com/2015/04/28/asia/kathmandu.jpg	Mozilla/5.0 (Linux; U; Android 4.4.2; en-US; SAMSUNG-SM-N900A Build/KOT49H) CNN/2.1.1 	
RK2FQ9PWZVW52	 2015 04 28 06 37 45919	 2015 04 28 06 37 45988	http://adclick.g.doubleclick.net/pics/click/?=	 Mozilla/5.0 (Linux; U; Android 4.4.2; en-US; SAMSUNG-SM-N900A Build/KOT49H) CNN/2.1.1 	
RK2FQ9PWZVW52	 2015 04 28 06 37 34957	 2015 04 28 06 37 34996	
http://www.google-analytics.com/__utm.gif?
utmwv=4.9mi	 Mozilla/5.0 (Linux; U; Android 4.4.2; en-US; SAMSUNG-SM-N900A Build/KOT49H) CNN/2.1.1 	
RK2FQ9PWZVW52	 2015 04 28 06 42 09 883	 2015 04 28 06 42 10 467	
http://www.cnn.com/2015/04/25/world/nepal-
earthquake-how-to-help/index.html	 Mozilla/5.0 (Linux; U; Android 4.4.2; en-US; SAMSUNG-SM-N900A Build/KOT49H) CNN/2.1.1 	
….. (images being loaded here)	 …….	
RK2FQ9PWZVW52	 2015 04 28 06 43 03 234	 2015 04 28 06 06 12 334	http://www.nrcs.org	 Mozilla/5.0 (Linux; U; Android 4.4.2; en-US; SAMSUNG-SM-N900A Build/KOT49H) 	
…..	 …..	 …..	 …..	 …	
RK2FQ9PWZVW52	 2015 04 28 09 45 05 732	
2015 04 28 09 45 05
812	 http://wsj.com	
Mozilla/5.0 (iPad; CPU OS 8_1 like Mac OS X) AppleWebKit/600.1.4 (KHTML, like Gecko) Version/
8.0 Mobile/12B410 Safari	
…..	 …..	 …..	 …	 …	
RK2FQ9PWZVW52	 2015 04 28 17 03 14 204	 2015 04 28 17 03 14 269	http://wsj.com	
Mozilla/5.0 (iPad; CPU OS 8_1 like Mac OS X) AppleWebKit/600.1.4 (KHTML, like Gecko) Version/
8.0 Mobile/12B410 Safari	
…..	 …..	 …..	 …	 …	
RK2FQ9PWZVW52	 2015 04 28 18 19 56 459	 2015 04 28 18 19 56 509	https://69.63.178.45	
…..	 …..	 …..	 …	 …	
RK2FQ9PWZVW52	 2015 04 28 21 23 25 754	 2015 04 28 21 23 25 876	http://23.13.201.71	 netflix-ios-app
A Day in the Life: Data Perspective
•  Capture and collate raw subscriber data
•  Sessionize and enrich clickstream data with location, device. and other data, calculate subscriber
usage metrics
SubscriberId	 DeviceNAME	 PUBLISHER	
Category-
Subcategory	
Application
Name	 SESSION START	 SESSION END	 PAGE_VIEWS	 HITS	 BYTES	 LOCATION	
RK2FQ9PWZVW52	Samsung Galaxy S6	 CNN News	
News-International
News	 CNN App	 2015 04 28 06 37 04 512	 2015 04 28 06 42 10 467	 4	 45	 539123	 NY	
RK2FQ9PWZVW52	 Samsung Galaxy S6	 Red Cross	
Non Profit &
Charities-Institutions	 Browser	 2015 04 28 06 43 03 234	 2015 04 28 06 53 03 874	 2	 7	 383372	 NY	
RK2FQ9PWZVW52	 Apple iPad	
Wall Street
Journal	
News-Business &
Finance News	 Safari Browser	 2015 04 28 09 45 05 732	 2015 04 28 09 55 05 732	 4	 40	 600272	 NY	
RK2FQ9PWZVW52	 Apple iPad	
Wall Street
Journal	
News-Business &
Finance News	 Safari Browser	 2015 04 28 17 03 14 204	 2015 04 28 17 23 14 204	 5	 35	 801714	 NY	
RK2FQ9PWZVW52
	
Apple iPad	
	 Facebook	
Social Media &
Networking-Social
Networking	 -	
2015 04 28 18 19 56 459	
	
2015 04 28 18 23 21 459	
	 318	 5041054	 Boston	
RK2FQ9PWZVW52
	
Apple iPad	
	 Netflix	
Media &
Entertainment-Online
Video	 Ne&lix	App	
2015 04 28 21 23 25 876	
	
2015 04 28 23 23 24 325	
	 6	 2330	 295121789	 Boston	
Compute subscriber-level metrics and aggregates
…enrich with information about content (websites or apps) and
categorization, devices, and locations
Aggregation and Enrichment
Insights: Marketing to Prepaid Users
•  With data science, operators can infer gender
and approximate age from subscriber activity
•  Classify according to segmentation schemes
(e.g., who does unknown subscriber resemble
from their activity)
We can offer advertisers anonymized
subscriber info mapped to standard
marketing/advertising categories (e.g.,
IAB) based on activity
Marketing Questions We Can Answer with Analytics
• How will subscribers respond
to changes in pricing?
• How do we market to
anonymous pre-paid
subscribers?
• Who’s likely to respond to an
offer?
• Which OTT apps threaten
our own branded apps?
• Which groups should we
target with advertising?
Pivotal and
Hortonworks are
partnering to help
companies use their
data for better
customer outcomes
Learn more
•  Videos: bit.ly/MADlibvideos
•  Project: madlib.incubator.apache.org
•  Downloads: bit.ly/getMADlib
•  Videos: bit.ly/HDBvideos
•  Project: hawq.incubator.apache.org
•  Commercial: pivotal.io/pivotal-hdb
•  Downloads: bit.ly/getHDB
Let’s build something
MEANINGFUL
Pivotal - Advanced Analytics for Telecommunications

Contenu connexe

Tendances

Hortonworks, Novetta and Noble Energy Webinar
Hortonworks, Novetta and Noble Energy Webinar Hortonworks, Novetta and Noble Energy Webinar
Hortonworks, Novetta and Noble Energy Webinar
Hortonworks
 

Tendances (20)

Eliminating the Challenges of Big Data Management Inside Hadoop
Eliminating the Challenges of Big Data Management Inside HadoopEliminating the Challenges of Big Data Management Inside Hadoop
Eliminating the Challenges of Big Data Management Inside Hadoop
 
Implementing a Data Lake with Enterprise Grade Data Governance
Implementing a Data Lake with Enterprise Grade Data GovernanceImplementing a Data Lake with Enterprise Grade Data Governance
Implementing a Data Lake with Enterprise Grade Data Governance
 
A Comprehensive Approach to Building your Big Data - with Cisco, Hortonworks ...
A Comprehensive Approach to Building your Big Data - with Cisco, Hortonworks ...A Comprehensive Approach to Building your Big Data - with Cisco, Hortonworks ...
A Comprehensive Approach to Building your Big Data - with Cisco, Hortonworks ...
 
Falcon Meetup
Falcon Meetup Falcon Meetup
Falcon Meetup
 
Simplify and Secure your Hadoop Environment with Hortonworks and Centrify
Simplify and Secure your Hadoop Environment with Hortonworks and CentrifySimplify and Secure your Hadoop Environment with Hortonworks and Centrify
Simplify and Secure your Hadoop Environment with Hortonworks and Centrify
 
HPE and Hortonworks join forces to Deliver Healthcare Transformation
HPE and Hortonworks join forces to Deliver Healthcare TransformationHPE and Hortonworks join forces to Deliver Healthcare Transformation
HPE and Hortonworks join forces to Deliver Healthcare Transformation
 
Eric Baldeschwieler Keynote from Storage Developers Conference
Eric Baldeschwieler Keynote from Storage Developers ConferenceEric Baldeschwieler Keynote from Storage Developers Conference
Eric Baldeschwieler Keynote from Storage Developers Conference
 
Hortonworks, Novetta and Noble Energy Webinar
Hortonworks, Novetta and Noble Energy Webinar Hortonworks, Novetta and Noble Energy Webinar
Hortonworks, Novetta and Noble Energy Webinar
 
Optimizing your Modern Data Architecture - with Attunity, RCG Global Services...
Optimizing your Modern Data Architecture - with Attunity, RCG Global Services...Optimizing your Modern Data Architecture - with Attunity, RCG Global Services...
Optimizing your Modern Data Architecture - with Attunity, RCG Global Services...
 
Streamline Apache Hadoop Operations with Apache Ambari and SmartSense
Streamline Apache Hadoop Operations with Apache Ambari and SmartSenseStreamline Apache Hadoop Operations with Apache Ambari and SmartSense
Streamline Apache Hadoop Operations with Apache Ambari and SmartSense
 
Hortonworks Protegrity Webinar: Leverage Security in Hadoop Without Sacrifici...
Hortonworks Protegrity Webinar: Leverage Security in Hadoop Without Sacrifici...Hortonworks Protegrity Webinar: Leverage Security in Hadoop Without Sacrifici...
Hortonworks Protegrity Webinar: Leverage Security in Hadoop Without Sacrifici...
 
Your Self-Driving Car - How Did it Get So Smart?
Your Self-Driving Car - How Did it Get So Smart?Your Self-Driving Car - How Did it Get So Smart?
Your Self-Driving Car - How Did it Get So Smart?
 
Splunk-hortonworks-risk-management-oct-2014
Splunk-hortonworks-risk-management-oct-2014Splunk-hortonworks-risk-management-oct-2014
Splunk-hortonworks-risk-management-oct-2014
 
Overcoming the AI hype — and what enterprises should really focus on
Overcoming the AI hype — and what enterprises should really focus onOvercoming the AI hype — and what enterprises should really focus on
Overcoming the AI hype — and what enterprises should really focus on
 
3 CTOs Discuss the Shift to Next-Gen Analytic Ecosystems
3 CTOs Discuss the Shift to Next-Gen Analytic Ecosystems3 CTOs Discuss the Shift to Next-Gen Analytic Ecosystems
3 CTOs Discuss the Shift to Next-Gen Analytic Ecosystems
 
Powering Big Data Success On-Prem and in the Cloud
Powering Big Data Success On-Prem and in the CloudPowering Big Data Success On-Prem and in the Cloud
Powering Big Data Success On-Prem and in the Cloud
 
What's New in Apache Hive 3.0?
What's New in Apache Hive 3.0?What's New in Apache Hive 3.0?
What's New in Apache Hive 3.0?
 
Getting to What Matters: Accelerating Your Path Through the Big Data Lifecycl...
Getting to What Matters: Accelerating Your Path Through the Big Data Lifecycl...Getting to What Matters: Accelerating Your Path Through the Big Data Lifecycl...
Getting to What Matters: Accelerating Your Path Through the Big Data Lifecycl...
 
Hortonworks - What's Possible with a Modern Data Architecture?
Hortonworks - What's Possible with a Modern Data Architecture?Hortonworks - What's Possible with a Modern Data Architecture?
Hortonworks - What's Possible with a Modern Data Architecture?
 
HDP Advanced Security: Comprehensive Security for Enterprise Hadoop
HDP Advanced Security: Comprehensive Security for Enterprise HadoopHDP Advanced Security: Comprehensive Security for Enterprise Hadoop
HDP Advanced Security: Comprehensive Security for Enterprise Hadoop
 

En vedette

En vedette (20)

Top 5 Strategies for Retail Data Analytics
Top 5 Strategies for Retail Data AnalyticsTop 5 Strategies for Retail Data Analytics
Top 5 Strategies for Retail Data Analytics
 
Edw Optimization Solution
Edw Optimization Solution Edw Optimization Solution
Edw Optimization Solution
 
Getting involved with Open Source at the ASF
Getting involved with Open Source at the ASFGetting involved with Open Source at the ASF
Getting involved with Open Source at the ASF
 
S3Guard: What's in your consistency model?
S3Guard: What's in your consistency model?S3Guard: What's in your consistency model?
S3Guard: What's in your consistency model?
 
Hortonworks Data Cloud for AWS
Hortonworks Data Cloud for AWS Hortonworks Data Cloud for AWS
Hortonworks Data Cloud for AWS
 
The path to a Modern Data Architecture in Financial Services
The path to a Modern Data Architecture in Financial ServicesThe path to a Modern Data Architecture in Financial Services
The path to a Modern Data Architecture in Financial Services
 
Hive - 1455: Cloud Storage
Hive - 1455: Cloud StorageHive - 1455: Cloud Storage
Hive - 1455: Cloud Storage
 
How to Use Apache Zeppelin with HWX HDB
How to Use Apache Zeppelin with HWX HDBHow to Use Apache Zeppelin with HWX HDB
How to Use Apache Zeppelin with HWX HDB
 
How Universities Use Big Data to Transform Education
How Universities Use Big Data to Transform EducationHow Universities Use Big Data to Transform Education
How Universities Use Big Data to Transform Education
 
Hortonworks Data in Motion Webinar Series Part 7 Apache Kafka Nifi Better Tog...
Hortonworks Data in Motion Webinar Series Part 7 Apache Kafka Nifi Better Tog...Hortonworks Data in Motion Webinar Series Part 7 Apache Kafka Nifi Better Tog...
Hortonworks Data in Motion Webinar Series Part 7 Apache Kafka Nifi Better Tog...
 
Scaling real time streaming architectures with HDF and Dell EMC Isilon
Scaling real time streaming architectures with HDF and Dell EMC IsilonScaling real time streaming architectures with HDF and Dell EMC Isilon
Scaling real time streaming architectures with HDF and Dell EMC Isilon
 
Hortonworks technical workshop operations with ambari
Hortonworks technical workshop   operations with ambariHortonworks technical workshop   operations with ambari
Hortonworks technical workshop operations with ambari
 
Delivering a Flexible IT Infrastructure for Analytics on IBM Power Systems
Delivering a Flexible IT Infrastructure for Analytics on IBM Power SystemsDelivering a Flexible IT Infrastructure for Analytics on IBM Power Systems
Delivering a Flexible IT Infrastructure for Analytics on IBM Power Systems
 
Credit Card Analytics on a Connected Data Platform
Credit Card Analytics on a Connected Data PlatformCredit Card Analytics on a Connected Data Platform
Credit Card Analytics on a Connected Data Platform
 
Webinar Series Part 5 New Features of HDF 5
Webinar Series Part 5 New Features of HDF 5Webinar Series Part 5 New Features of HDF 5
Webinar Series Part 5 New Features of HDF 5
 
SAS - Hortonworks: Creating the Omnichannel Experience in Retail webinar marc...
SAS - Hortonworks: Creating the Omnichannel Experience in Retail webinar marc...SAS - Hortonworks: Creating the Omnichannel Experience in Retail webinar marc...
SAS - Hortonworks: Creating the Omnichannel Experience in Retail webinar marc...
 
The Power of your Data Achieved - Next Gen Modernization
The Power of your Data Achieved - Next Gen ModernizationThe Power of your Data Achieved - Next Gen Modernization
The Power of your Data Achieved - Next Gen Modernization
 
Double Your Hadoop Hardware Performance with SmartSense
Double Your Hadoop Hardware Performance with SmartSenseDouble Your Hadoop Hardware Performance with SmartSense
Double Your Hadoop Hardware Performance with SmartSense
 
Apache Hadoop 0.23
Apache Hadoop 0.23Apache Hadoop 0.23
Apache Hadoop 0.23
 
Alcumes de Ribadavia
Alcumes de RibadaviaAlcumes de Ribadavia
Alcumes de Ribadavia
 

Similaire à Pivotal - Advanced Analytics for Telecommunications

Powering Real-Time Big Data Analytics with a Next-Gen GPU Database
Powering Real-Time Big Data Analytics with a Next-Gen GPU DatabasePowering Real-Time Big Data Analytics with a Next-Gen GPU Database
Powering Real-Time Big Data Analytics with a Next-Gen GPU Database
Kinetica
 
Big Data Integration Webinar: Getting Started With Hadoop Big Data
Big Data Integration Webinar: Getting Started With Hadoop Big DataBig Data Integration Webinar: Getting Started With Hadoop Big Data
Big Data Integration Webinar: Getting Started With Hadoop Big Data
Pentaho
 

Similaire à Pivotal - Advanced Analytics for Telecommunications (20)

Smart Enterprise Big Data Bus for the Modern Responsive Enterprise- StreamAna...
Smart Enterprise Big Data Bus for the Modern Responsive Enterprise- StreamAna...Smart Enterprise Big Data Bus for the Modern Responsive Enterprise- StreamAna...
Smart Enterprise Big Data Bus for the Modern Responsive Enterprise- StreamAna...
 
Preventative Maintenance of Robots in Automotive Industry
Preventative Maintenance of Robots in Automotive IndustryPreventative Maintenance of Robots in Automotive Industry
Preventative Maintenance of Robots in Automotive Industry
 
Open Data Science Conference Big Data Infrastructure – Introduction to Hadoop...
Open Data Science Conference Big Data Infrastructure – Introduction to Hadoop...Open Data Science Conference Big Data Infrastructure – Introduction to Hadoop...
Open Data Science Conference Big Data Infrastructure – Introduction to Hadoop...
 
Solving enterprise challenges through scale out storage & big compute final
Solving enterprise challenges through scale out storage & big compute finalSolving enterprise challenges through scale out storage & big compute final
Solving enterprise challenges through scale out storage & big compute final
 
From an experiment to a real production environment
From an experiment to a real production environmentFrom an experiment to a real production environment
From an experiment to a real production environment
 
Powering Real-Time Big Data Analytics with a Next-Gen GPU Database
Powering Real-Time Big Data Analytics with a Next-Gen GPU DatabasePowering Real-Time Big Data Analytics with a Next-Gen GPU Database
Powering Real-Time Big Data Analytics with a Next-Gen GPU Database
 
Open Sourcing GemFire - Apache Geode
Open Sourcing GemFire - Apache GeodeOpen Sourcing GemFire - Apache Geode
Open Sourcing GemFire - Apache Geode
 
An Introduction to Apache Geode (incubating)
An Introduction to Apache Geode (incubating)An Introduction to Apache Geode (incubating)
An Introduction to Apache Geode (incubating)
 
Cloud-Scale BGP and NetFlow Analysis
Cloud-Scale BGP and NetFlow AnalysisCloud-Scale BGP and NetFlow Analysis
Cloud-Scale BGP and NetFlow Analysis
 
Horses for Courses: Database Roundtable
Horses for Courses: Database RoundtableHorses for Courses: Database Roundtable
Horses for Courses: Database Roundtable
 
UNV Are Dead - How to migrate to UNX in a few simple steps
UNV Are Dead - How to migrate to UNX in a few simple stepsUNV Are Dead - How to migrate to UNX in a few simple steps
UNV Are Dead - How to migrate to UNX in a few simple steps
 
Considering Bare Metal
Considering Bare MetalConsidering Bare Metal
Considering Bare Metal
 
VoltDB and Flytxt Present: Building a Single Technology Platform for Real-Tim...
VoltDB and Flytxt Present: Building a Single Technology Platform for Real-Tim...VoltDB and Flytxt Present: Building a Single Technology Platform for Real-Tim...
VoltDB and Flytxt Present: Building a Single Technology Platform for Real-Tim...
 
Big Data Integration Webinar: Getting Started With Hadoop Big Data
Big Data Integration Webinar: Getting Started With Hadoop Big DataBig Data Integration Webinar: Getting Started With Hadoop Big Data
Big Data Integration Webinar: Getting Started With Hadoop Big Data
 
JDD2014: Real Big Data - Scott MacGregor
JDD2014: Real Big Data - Scott MacGregorJDD2014: Real Big Data - Scott MacGregor
JDD2014: Real Big Data - Scott MacGregor
 
Data & Analytics - Session 1 - Big Data Analytics
Data & Analytics - Session 1 -  Big Data AnalyticsData & Analytics - Session 1 -  Big Data Analytics
Data & Analytics - Session 1 - Big Data Analytics
 
Panel with IPv6 CE Vendors
Panel with IPv6 CE VendorsPanel with IPv6 CE Vendors
Panel with IPv6 CE Vendors
 
Unified Framework for Real Time, Near Real Time and Offline Analysis of Video...
Unified Framework for Real Time, Near Real Time and Offline Analysis of Video...Unified Framework for Real Time, Near Real Time and Offline Analysis of Video...
Unified Framework for Real Time, Near Real Time and Offline Analysis of Video...
 
The Current And Future State Of Service Mesh
The Current And Future State Of Service MeshThe Current And Future State Of Service Mesh
The Current And Future State Of Service Mesh
 
IMCSummit 2015 - 1 IT Business - The Evolution of Pivotal Gemfire
IMCSummit 2015 - 1 IT Business  - The Evolution of Pivotal GemfireIMCSummit 2015 - 1 IT Business  - The Evolution of Pivotal Gemfire
IMCSummit 2015 - 1 IT Business - The Evolution of Pivotal Gemfire
 

Plus de Hortonworks

Plus de Hortonworks (20)

Hortonworks DataFlow (HDF) 3.3 - Taking Stream Processing to the Next Level
Hortonworks DataFlow (HDF) 3.3 - Taking Stream Processing to the Next LevelHortonworks DataFlow (HDF) 3.3 - Taking Stream Processing to the Next Level
Hortonworks DataFlow (HDF) 3.3 - Taking Stream Processing to the Next Level
 
IoT Predictions for 2019 and Beyond: Data at the Heart of Your IoT Strategy
IoT Predictions for 2019 and Beyond: Data at the Heart of Your IoT StrategyIoT Predictions for 2019 and Beyond: Data at the Heart of Your IoT Strategy
IoT Predictions for 2019 and Beyond: Data at the Heart of Your IoT Strategy
 
Getting the Most Out of Your Data in the Cloud with Cloudbreak
Getting the Most Out of Your Data in the Cloud with CloudbreakGetting the Most Out of Your Data in the Cloud with Cloudbreak
Getting the Most Out of Your Data in the Cloud with Cloudbreak
 
Johns Hopkins - Using Hadoop to Secure Access Log Events
Johns Hopkins - Using Hadoop to Secure Access Log EventsJohns Hopkins - Using Hadoop to Secure Access Log Events
Johns Hopkins - Using Hadoop to Secure Access Log Events
 
Catch a Hacker in Real-Time: Live Visuals of Bots and Bad Guys
Catch a Hacker in Real-Time: Live Visuals of Bots and Bad GuysCatch a Hacker in Real-Time: Live Visuals of Bots and Bad Guys
Catch a Hacker in Real-Time: Live Visuals of Bots and Bad Guys
 
HDF 3.2 - What's New
HDF 3.2 - What's NewHDF 3.2 - What's New
HDF 3.2 - What's New
 
Curing Kafka Blindness with Hortonworks Streams Messaging Manager
Curing Kafka Blindness with Hortonworks Streams Messaging ManagerCuring Kafka Blindness with Hortonworks Streams Messaging Manager
Curing Kafka Blindness with Hortonworks Streams Messaging Manager
 
Interpretation Tool for Genomic Sequencing Data in Clinical Environments
Interpretation Tool for Genomic Sequencing Data in Clinical EnvironmentsInterpretation Tool for Genomic Sequencing Data in Clinical Environments
Interpretation Tool for Genomic Sequencing Data in Clinical Environments
 
IBM+Hortonworks = Transformation of the Big Data Landscape
IBM+Hortonworks = Transformation of the Big Data LandscapeIBM+Hortonworks = Transformation of the Big Data Landscape
IBM+Hortonworks = Transformation of the Big Data Landscape
 
Premier Inside-Out: Apache Druid
Premier Inside-Out: Apache DruidPremier Inside-Out: Apache Druid
Premier Inside-Out: Apache Druid
 
Accelerating Data Science and Real Time Analytics at Scale
Accelerating Data Science and Real Time Analytics at ScaleAccelerating Data Science and Real Time Analytics at Scale
Accelerating Data Science and Real Time Analytics at Scale
 
TIME SERIES: APPLYING ADVANCED ANALYTICS TO INDUSTRIAL PROCESS DATA
TIME SERIES: APPLYING ADVANCED ANALYTICS TO INDUSTRIAL PROCESS DATATIME SERIES: APPLYING ADVANCED ANALYTICS TO INDUSTRIAL PROCESS DATA
TIME SERIES: APPLYING ADVANCED ANALYTICS TO INDUSTRIAL PROCESS DATA
 
Blockchain with Machine Learning Powered by Big Data: Trimble Transportation ...
Blockchain with Machine Learning Powered by Big Data: Trimble Transportation ...Blockchain with Machine Learning Powered by Big Data: Trimble Transportation ...
Blockchain with Machine Learning Powered by Big Data: Trimble Transportation ...
 
Delivering Real-Time Streaming Data for Healthcare Customers: Clearsense
Delivering Real-Time Streaming Data for Healthcare Customers: ClearsenseDelivering Real-Time Streaming Data for Healthcare Customers: Clearsense
Delivering Real-Time Streaming Data for Healthcare Customers: Clearsense
 
Making Enterprise Big Data Small with Ease
Making Enterprise Big Data Small with EaseMaking Enterprise Big Data Small with Ease
Making Enterprise Big Data Small with Ease
 
Webinewbie to Webinerd in 30 Days - Webinar World Presentation
Webinewbie to Webinerd in 30 Days - Webinar World PresentationWebinewbie to Webinerd in 30 Days - Webinar World Presentation
Webinewbie to Webinerd in 30 Days - Webinar World Presentation
 
Driving Digital Transformation Through Global Data Management
Driving Digital Transformation Through Global Data ManagementDriving Digital Transformation Through Global Data Management
Driving Digital Transformation Through Global Data Management
 
HDF 3.1 pt. 2: A Technical Deep-Dive on New Streaming Features
HDF 3.1 pt. 2: A Technical Deep-Dive on New Streaming FeaturesHDF 3.1 pt. 2: A Technical Deep-Dive on New Streaming Features
HDF 3.1 pt. 2: A Technical Deep-Dive on New Streaming Features
 
Hortonworks DataFlow (HDF) 3.1 - Redefining Data-In-Motion with Modern Data A...
Hortonworks DataFlow (HDF) 3.1 - Redefining Data-In-Motion with Modern Data A...Hortonworks DataFlow (HDF) 3.1 - Redefining Data-In-Motion with Modern Data A...
Hortonworks DataFlow (HDF) 3.1 - Redefining Data-In-Motion with Modern Data A...
 
Unlock Value from Big Data with Apache NiFi and Streaming CDC
Unlock Value from Big Data with Apache NiFi and Streaming CDCUnlock Value from Big Data with Apache NiFi and Streaming CDC
Unlock Value from Big Data with Apache NiFi and Streaming CDC
 

Dernier

Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Victor Rentea
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Safe Software
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
WSO2
 

Dernier (20)

Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot ModelMcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
Vector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptxVector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptx
 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistan
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
 
Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
Exploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusExploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with Milvus
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
 
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
 
Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
Six Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal OntologySix Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal Ontology
 

Pivotal - Advanced Analytics for Telecommunications

  • 1. background image: 960x540 pixels - send to back of slide and set to 80% transparency Advanced Analytics for Telecommunications Bob Glithero, Principal Product Marketing Manager Vineet Goel, Product Manager
  • 2. background image: 960x540 pixels - send to back of slide and set to 80% transparency Agenda •  Pivotal – Hortonworks Partnership •  Challenges in Customer Experience •  HDB: Hadoop-Native Analytics Database for Hortonworks Data Platform •  Sample Use Cases •  For More Information
  • 3. Pivotal HDB + Hortonworks Hadoop Partnering for Faster Value from Data ●  Leaders in open-source Hadoop ●  Managing, analyzing, and operationalizing data at scale ●  Joint support for ODPi promotes interoperability in Hadoop + Pivotal and Hortonworks’ strategic partnership marries Pivotal’s best-in-class SQL on Hadoop, analytical database, with Hortonworks’ best-in class expertise and support for Hadoop.
  • 4. You’re the third person I’ve been handed off to! Can’t anyone help me? 4
  • 5. I’m not seeing any alarms...why are our customers having poor service? 5
  • 6. Managing Experience is Complicated Then •  Basic handsets, embedded applications •  Simpler services - voice, SMS, WAP •  Experience influenced mostly inside the network Now •  From phones to hand-held computers •  Massive data volume, velocity, and variety from millions of apps and services •  MNOs held responsible for all aspects of service, whether inside or outside the network
  • 7. CSPs Increasingly Competing on QoE Trying to understand how network performance impacts experience When service is degraded, CSPs need to quickly understand: Is the problem inside or outside the network? Which subscribers are impacted? What needs attention first?
  • 8. Common Operator Challenges Network Operations Customer Care Marketing Increase monetization, offset voice, SMS revenue loss Reduce churn and credits, cost to serve Reduce complexity, increase visibility, increase QoE
  • 9. background image: 960x540 pixels - send to back of slide and set to 80% transparency Operators are turning to their data to solve these challenges How do we analyze data in an efficient, cost-effective way to transform customer experience?
  • 10. High performance, interactive SQL queries on Hadoop HDB: The Hadoop Native SQL Database ●  Highly efficient MPP (massively parallel processing) ●  Low-latency ●  Petabyte scalability ●  ACID transaction support ●  SQL-92, 99, 2003 compatibility ●  Advanced cost-based optimizer DATA LAKE SQL App BUSINESS ANALYSTS DATA SCIENTISTS
  • 11. Advanced Analytics Performance Exceptional MPP performance, low latency, petabyte scalability, ACID reliability, fault tolerance Most Complete Language Compliance Higher degree of SQL compatibility, SQL-92, 99, 2003, OLAP, leverage existing SQL skills Best-in-class Query Optimizer Maximize performance and do advanced queries with confidence Elastic Architecture for Scalability Scale-up/down or scale-in/out, expand/ shrink clusters on the fly Tightly integrated w/ MADlib Machine Learning Advanced MPP analytics, data science at scale, directly on Hadoop data HDB / HAWQ Advantages MAD
  • 12. ●  Discover New Rela/onships ●  Enable Data Science ●  Analyze External Sources ●  Query All Data Types! Mul/-level Fault Tolerance Granular Authoriza/on Resource Pools + YARN Mul$-tenancy + Security ANSI SQL Standard OLAP Extensions JDBC ODBC Connec/vity MPP Architecture Online Expansion Hadoop / HDFS Petabyte Scale Cost-Based OpXYZizer Dynamic Pipelining ACID + Transac/onal Ambari Management Machine Learning Data Federa/on Language Extensions Hardened, 10+ Years Tested, Produc/on Proven Opera$ons + Extensibility HDFS Na/ve File Formats ●  Manage Mul/ple Workloads ●  Petabyte Scale Analy/cs ●  Sub-second Performance ●  Leverage Exis/ng Skills & Tools ●  Easily Integrate with Other Tools Compression + Par//oning Core compliance ●  Well Integrated with Hortonworks Data PlaZorm HDB + HDP Marketecture
  • 13. 13 Faster Insight with In-Database Analytics Pivotal HDB / Apache HAWQ (incubating) Low-latency, MPP analytic database with full ANSI SQL support running natively on Hortonworks HDP Apache MADlib (incubating) Scale out, SQL-based machine learning within HDB/HAWQ, Greenplum, and PostgreSQL databases +
  • 14. 14 Top MADlib Use Cases •  Fraud detection •  Risk analysis •  Customer experience •  Marketing •  Predictive maintenance
  • 15. Telco uses HDB to analyze and improve call quality 2bn call records per day •  Overwhelmed traditional data warehouse Hadoop and HDB •  5x data stored at half the cost •  Familiar SQL interface to analyze 3 months worth of dropped call data DATA LAKE
  • 16. 16 How could a network operations team apply analytics to improve experience for its network services?
  • 17. What Data Is Needed? Service Assurance Customer Care Marketing • Network Performance data (GTP probe data) • HTTP Click Stream Records • Flow Records • Network & Device Reference Data • Topology and location • HTTP Click Stream Records • Flow Records • Network Performance data (GTP probe data) • CRM data (account, device information) • Service Request Records • HTTP Click Stream Records • Flow Records • CRM data (account, device information)
  • 18. Constructing KQIs from performance indicators 84% Speed Latency Effective Throughput Integrity Drops Time-Outs Cut-Offs Failures Retainability Failure % Response time Access time Accessibility Voice QoE Data capture Data science •  xDRs •  NetFlow •  Probes Data processing Accessibility Quality Retainability
  • 19. In-Database Analytics with HDB and MADlib Application/ Content Data •  Raw Usage •  Logs •  (HTTP, Flow, Other) HDFS HBase Hive HDB/HAWQ In-DB AnalyticsNetwork Data •  Probes (GTP-C/U) •  xDRs •  Case management •  CRM •  Billing •  Device inventory •  Network topology •  Geolocation maps B/OSS Data PXF PXF MPP Query Execution ANSI SQL •  SQL-based •  Over 50 data science functions •  UDFs •  Offline modeling •  Batch queries •  Reporting/viz with SQL-based tools + Native or PXF
  • 20. 20 How could marketing teams use analytics to better target subscribers for promotions and advertising?
  • 21. Blended Mobile ARPU is Declining Loss of voice and SMS ARPU from competition, free apps Data revenues not offsetting voice, SMS losses MNOs seeking new monetization options Source: IHS Technology Mobile ARPU Forecast, 2016
  • 22. Need for Behavioral Insights •  CSPs need to maximize subscriber yields to offset declining revenues •  Marketers have little information to market to anonymous prepaid subscribers •  Need to protect current revenue from competition from over-the-top (OTT) apps and services
  • 23. Morning: New York •  Starts on Samsung Galaxy S6 •  On CNN, sees news on earthquake •  Donates via Red Cross Society •  Later: Switches to iPad – same account plan •  Checks market close on WSJ.com A Day in the Life: User Perspective Evening: Boston •  Checks Facebook page •  Streams Netflix
  • 24. SubscriberId StartTimeStamp EndTimeStamp URL User Agent RK2FQ9PWZVW52 2015 04 28 06 37 04 512 2015 04 28 06 37 04 543 http://www.cnn.com Mozilla/5.0 (Linux; U; Android 4.4.2; en-US; SAMSUNG-SM-N900A Build/KOT49H) CNN/2.1.1 RK2FQ9PWZVW52 2015 04 28 06 37 05 546 2015 04 28 06 37 04 623 http://www.cnn.com/world Mozilla/5.0 (Linux; U; Android 4.4.2; en-US; SAMSUNG-SM-N900A Build/KOT49H) CNN/2.1.1 RK2FQ9PWZVW52 2015 04 28 06 37 19 529 2015 04 28 06 37 19 599 http://www.cnn.com/2015/04/28/asia/flight-delhi- nepal-earthquake/index.html Mozilla/5.0 (Linux; U; Android 4.4.2; en-US; SAMSUNG-SM-N900A Build/KOT49H) CNN/2.1.1 RK2FQ9PWZVW52 2015 04 28 06 37 23710 2015 04 28 06 37 23 770 http://www.cnn.com/2015/04/28/asia/kathmandu.jpg Mozilla/5.0 (Linux; U; Android 4.4.2; en-US; SAMSUNG-SM-N900A Build/KOT49H) CNN/2.1.1 RK2FQ9PWZVW52 2015 04 28 06 37 45919 2015 04 28 06 37 45988 http://adclick.g.doubleclick.net/pics/click/?= Mozilla/5.0 (Linux; U; Android 4.4.2; en-US; SAMSUNG-SM-N900A Build/KOT49H) CNN/2.1.1 RK2FQ9PWZVW52 2015 04 28 06 37 34957 2015 04 28 06 37 34996 http://www.google-analytics.com/__utm.gif? utmwv=4.9mi Mozilla/5.0 (Linux; U; Android 4.4.2; en-US; SAMSUNG-SM-N900A Build/KOT49H) CNN/2.1.1 RK2FQ9PWZVW52 2015 04 28 06 42 09 883 2015 04 28 06 42 10 467 http://www.cnn.com/2015/04/25/world/nepal- earthquake-how-to-help/index.html Mozilla/5.0 (Linux; U; Android 4.4.2; en-US; SAMSUNG-SM-N900A Build/KOT49H) CNN/2.1.1 ….. (images being loaded here) ……. RK2FQ9PWZVW52 2015 04 28 06 43 03 234 2015 04 28 06 06 12 334 http://www.nrcs.org Mozilla/5.0 (Linux; U; Android 4.4.2; en-US; SAMSUNG-SM-N900A Build/KOT49H) ….. ….. ….. ….. … RK2FQ9PWZVW52 2015 04 28 09 45 05 732 2015 04 28 09 45 05 812 http://wsj.com Mozilla/5.0 (iPad; CPU OS 8_1 like Mac OS X) AppleWebKit/600.1.4 (KHTML, like Gecko) Version/ 8.0 Mobile/12B410 Safari ….. ….. ….. … … RK2FQ9PWZVW52 2015 04 28 17 03 14 204 2015 04 28 17 03 14 269 http://wsj.com Mozilla/5.0 (iPad; CPU OS 8_1 like Mac OS X) AppleWebKit/600.1.4 (KHTML, like Gecko) Version/ 8.0 Mobile/12B410 Safari ….. ….. ….. … … RK2FQ9PWZVW52 2015 04 28 18 19 56 459 2015 04 28 18 19 56 509 https://69.63.178.45 ….. ….. ….. … … RK2FQ9PWZVW52 2015 04 28 21 23 25 754 2015 04 28 21 23 25 876 http://23.13.201.71 netflix-ios-app A Day in the Life: Data Perspective •  Capture and collate raw subscriber data •  Sessionize and enrich clickstream data with location, device. and other data, calculate subscriber usage metrics
  • 25. SubscriberId DeviceNAME PUBLISHER Category- Subcategory Application Name SESSION START SESSION END PAGE_VIEWS HITS BYTES LOCATION RK2FQ9PWZVW52 Samsung Galaxy S6 CNN News News-International News CNN App 2015 04 28 06 37 04 512 2015 04 28 06 42 10 467 4 45 539123 NY RK2FQ9PWZVW52 Samsung Galaxy S6 Red Cross Non Profit & Charities-Institutions Browser 2015 04 28 06 43 03 234 2015 04 28 06 53 03 874 2 7 383372 NY RK2FQ9PWZVW52 Apple iPad Wall Street Journal News-Business & Finance News Safari Browser 2015 04 28 09 45 05 732 2015 04 28 09 55 05 732 4 40 600272 NY RK2FQ9PWZVW52 Apple iPad Wall Street Journal News-Business & Finance News Safari Browser 2015 04 28 17 03 14 204 2015 04 28 17 23 14 204 5 35 801714 NY RK2FQ9PWZVW52 Apple iPad Facebook Social Media & Networking-Social Networking - 2015 04 28 18 19 56 459 2015 04 28 18 23 21 459 318 5041054 Boston RK2FQ9PWZVW52 Apple iPad Netflix Media & Entertainment-Online Video Ne&lix App 2015 04 28 21 23 25 876 2015 04 28 23 23 24 325 6 2330 295121789 Boston Compute subscriber-level metrics and aggregates …enrich with information about content (websites or apps) and categorization, devices, and locations Aggregation and Enrichment
  • 26. Insights: Marketing to Prepaid Users •  With data science, operators can infer gender and approximate age from subscriber activity •  Classify according to segmentation schemes (e.g., who does unknown subscriber resemble from their activity) We can offer advertisers anonymized subscriber info mapped to standard marketing/advertising categories (e.g., IAB) based on activity
  • 27. Marketing Questions We Can Answer with Analytics • How will subscribers respond to changes in pricing? • How do we market to anonymous pre-paid subscribers? • Who’s likely to respond to an offer? • Which OTT apps threaten our own branded apps? • Which groups should we target with advertising?
  • 28. Pivotal and Hortonworks are partnering to help companies use their data for better customer outcomes
  • 29. Learn more •  Videos: bit.ly/MADlibvideos •  Project: madlib.incubator.apache.org •  Downloads: bit.ly/getMADlib •  Videos: bit.ly/HDBvideos •  Project: hawq.incubator.apache.org •  Commercial: pivotal.io/pivotal-hdb •  Downloads: bit.ly/getHDB