How to Troubleshoot Apps for the Modern Connected Worker
Â
Big Data & Analytics Architecture
1. Advanced Analytics Platform Deep Dive
Components, Patterns, Architecture Decisions
ISA-3637 (Tue Nov 5 11:15 AM â 12:15 AM)
Dr. Arvind Sathi asathi@us.ibm.com
Richard Harken rharken@us.ibm.com
Tommy Eunice teunice@us.ibm.com
Mathews Thomas Mathews@us.ibm.com
Š 2013 IBM Corporation
2. Please note
IBMâs statements regarding its plans, directions, and intent are subject to
change or withdrawal without notice at IBMâs sole discretion.
Information regarding potential future products is intended to outline our general
product direction and it should not be relied on in making a purchasing decision.
The information mentioned regarding potential future products is not a
commitment, promise, or legal obligation to deliver any material, code or
functionality. Information about potential future products may not be
incorporated into any contract. The development, release, and timing of any
future features or functionality described for our products remains at our sole
discretion.
Performance is based on measurements and projections using standard IBM
benchmarks in a controlled environment. The actual throughput or performance
that any user will experience will vary depending upon many factors, including
considerations such as the amount of multiprogramming in the userâs job
stream, the I/O configuration, the storage configuration, and the workload
processed. Therefore, no assurance can be given that an individual user will
achieve results similar to those stated here.
3. Acknowledgements and Disclaimers
Availability. References in this presentation to IBM products, programs, or services do not imply that they will be available in all countries in
which IBM operates.
The workshops, sessions and materials have been prepared by IBM or the session speakers and reflect their own views. They are provided for
informational purposes only, and are neither intended to, nor shall have the effect of being, legal or other guidance or advice to any participant.
While efforts were made to verify the completeness and accuracy of the information contained in this presentation, it is provided AS-IS without
warranty of any kind, express or implied. IBM shall not be responsible for any damages arising out of the use of, or otherwise related to, this
presentation or any other materials. Nothing contained in this presentation is intended to, nor shall have the effect of, creating any warranties or
representations from IBM or its suppliers or licensors, or altering the terms and conditions of the applicable license agreement governing the use
of IBM software.
All customer examples described are presented as illustrations of how those customers have used IBM products and the results they may have
achieved. Actual environmental costs and performance characteristics may vary by customer. Nothing contained in these materials is intended
to, nor shall have the effect of, stating or implying that any activities undertaken by you will result in any specific sales, revenue growth or other
results.
Š Copyright IBM Corporation 2013. All rights reserved.
â˘U.S. Government Users Restricted Rights - Use, duplication or disclosure restricted by GSA ADP Schedule Contract with
IBM Corp.
â˘Please update paragraph below for the particular product or family brand trademarks you mention such as WebSphere, DB2,
Maximo, Clearcase, Lotus, etc
IBM, the IBM logo, ibm.com, [IBM Brand, if trademarked], and [IBM Product, if trademarked] are trademarks or registered
trademarks of International Business Machines Corporation in the United States, other countries, or both. If these and other IBM
trademarked terms are marked on their first occurrence in this information with a trademark symbol (ÂŽ or â˘), these symbols
indicate U.S. registered or common law trademarks owned by IBM at the time this information was published. Such trademarks may
also be registered or common law trademarks in other countries. A current list of IBM trademarks is available on the Web at
âCopyright and trademark informationâ at www.ibm.com/legal/copytrade.shtml
If you have mentioned trademarks that are not from IBM, please update and add the following lines:
[Insert any special 3rd party trademark names/attributions here]
Other company, product, or service names may be trademarks or service marks of others.
4. Content
⢠Use cases to support Business Architecture
⢠Components to support Application Architecture
⢠Data Integration
⢠Privacy Management & Archiving
⢠Location & Lifestyle Analytics
⢠Adaptive Analytics
⢠Momentum and Conclusions
5. AAP â Telecommunications Use Cases
Industry
Imperatives
MAJOR use
cases
Create & Deliver
Smarter Services
Transform
Operations
Location Based Services
IT Infrastructure Transformation
(Traditional to Big Data)
Cross Industry Solutions
Voice & Data Fraud
Build Smarter
Networks
Personalize
Customer
Engagements
Network Analytics
Pro Active Call Center
Network Infrastructure Planning
(Performance, Capacity, Usage)
Customer Data/Location
Monetization
Product Knowledge Hub
Smarter Campaigns
Customer Knowledge Hub
Social Media Insight
Emerging
Use Cases
ď§ Smarter Advertising
ď§ Customized Customer
Marketing
ď§ 3rd Party APIâs
ď§ Cloud services for
SMEs, enterprises
ď§ Contactless services
(payments and banking)
ď§ M2M (smart cars, eHealth)
ď§ Tiered Services
ď§ Big Data Scale
ď§ Investment Decisions
ď§ Lower storage
requirements
ď§ Smarter Returns
ď§ Analyze data before it
lands â then store only
what you need
ď§ New analytic models
ď§ Share critical
information across the
enterprise vs. deliver
multiple copies of the
data
ď§ Traditional
Infrastructure
Optimization
ď§ Product Knowledge Hub
ď§ Content Network
Distribution
ď§ Proactive Device
Management
ď§ Network Fault Prevention
ď§ ICTO (Energy Savings)
ď§ Real Time Traffic
Optimization
ď§ Network Abuse from
excessive data users
ď§ Discrete on-line charging
for quality of experience
ď§ Real time automated
capacity management for
dropped calls
ď§ SON Capacity
Management for special
events (traffic offload)
ď§ Service Migration
ď§ Social Advocacy
ď§ Cross Offering
Transparency
ď§ Smarter Customer
Interaction &
Engagement
ď§ Real-time Customer
Experience Insight
ď§ Smarter Campaigns
ď§ Customer Retention
ď§ Micro Segmentation
Marketing
ď§ Next Best Offer
ď§ Retail cross Channel
optimization
6. How to turn streaming noisy Telco Location data into meaningful location, then
discover customer insights
Location Pattern Analytics
Stream data
Call Detail
Records
SMS Voice
GPS Tracking
Wifi off load
Reference Data
Cell Tower
Wifi AP Maps
GIS, POI
Special Service
Numbers
e.g bank, 1-800
Big Data
Integration
Mobile Location Data
Processing: Map mapping,
Business rules et.
Spatio-Temporal Event
Association Analysis
Analyzable Location Event Meaningful Location
Data
Who, when, where and what subscriberId:
home:
subscriberId:
Work:
Timestamp:
POIs & period âŚ
Position: latitude +
Sequence of
longitude
meaningful
Precision: 0~2 km
LocationsâŚ
Direction: nullable
Commute means:
Speed: nullable
car/subway/bus
Activity : nullable
Micro segmentaton
Business traveler
Regular commuter
Heavy driver
Social Butterfly
Mom
âŚ..
Location Patterns on
Individual and Group
level
ďźEvery Sunday
noon, Bob goes to
xxx mall to shopping
and has lunch
ďźEvery Thursday
afternoon, Bob goes
to customer site at
XXX
ďźâŚ..
7. Mobile Couponing Use Case
1) Contacts Offertel Communications to
run campaign for a new store next to a
movie theater
2) Opts-in to receive mobile
coupons from the Telco
7) Posts on twitter,
Facebook public fan
page for Cuppa
Heaven
Telco
Customer Profile
Campaign Delivery
System
6A) Receives mobile
6A) Receives
coupon for new
6B) Deliver
mobile coupon
Cuppa Heaven store Coupons to
for new Cuppa
mobile opt-out
Heaven store
clients via
email & web
site
7) Monitor
Campaign
Performance
5) Priority list
transferred to
conduct
campaign
Advanced
Analytics
Platform
Customer Action
Telco clients who have
opted out of Mobile
Cuppa Heaven/Offertel Action
coupons
3) Use Social media to establish
âOpinion Leadersâ, potential
coffee drinkers, movie goers
4) Driving habits, coffee
preference, & opinion leaders
used to prioritize customer target
list
8. AAP â Media and Entertainment Use Cases
Organizational
FOCUS areas
Create differentiated customer experiences
âConnected Consumerâ
Build an agile digital supply chain
âSmarter Mediaâ
Audience & Marketing Optimization
Industry Team
use cases
Operations Analysis & Optimization
Multi-Channel Enablement
Business Process Transformation
Infrastructure Mgmt & Security
Digital Commerce Optimization
(sales play)
360o View of the Customer
Customer & Market Insight
MAJOR use cases
Advertising Optimization
Media, Metadata & Optimization.
â˘Social Profiling/ Sentiment Analysis
â˘Churn Optimization
â˘Customer Care Optimization
â˘Audience/ Viewing Duplication
â˘Audience Composition Index
â˘Multi-Platform Ad Performance
â˘Advertiser Revenue Analysis
â˘Real Time Audience Targeting
â˘CRM Optimization
â˘Real-time ad targeting
â˘Ad inventory Optimization
â˘Real-time ad reporting
â˘Search engine optimization
â˘Campaign optimization (in-flight)
â˘Marketing campaign effectiveness
â˘Network & infrastructure optimization
â˘Network Demand Forecasting
â˘Content optimization
â˘Content demand forecasting
â˘IP Rights Optimization
9. AAP for Real-time Bidding of Advertisements
Telco Website
Content
Provider
Turn
Telco
Flex Tag
TURN DMP
Location
Events /
xDR
Telco
Data
Usage
Data
Integration
Campaign
Feedback
Customer
Predictive
Models
TURN DSP
Campaign
Mgmt
Advanced Analytics Platform
Real-time
Scoring
Bid Req
Customer
Data
Campaign
Details
Analytics
Visualization
Additional data (e.g. Offer acceptance, location)
Offer &
Response
Bid Req
Offer &
Response
10. Content
⢠Use cases to support Business Architecture
⢠Components to support Application Architecture
⢠Data Integration
⢠Privacy Management & Archiving
⢠Location & Lifestyle Analytics
⢠Adaptive Analytics
⢠Momentum and Conclusions
11. New Architecture to Leverage All Data and Analytics
Streams
Data in
Motion
Information
Ingestion
and
Operational
Information
ď§ Stream Processing
ď§ Data Integration
ď§ Master Data
Data at
Rest
Intelligence
Analysis
Real-time
Analytics
ď§
ď§
ď§
ď§
Video/Audio
Network/Sensor
Entity Analytics
Predictive
Landing
Area,
Analytics
Zone
and Archive
Exploration
,
Integrated
Warehouse
,
and Mart
Zones
Decision
Management
BI and Predictive
Analytics
Navigation
and Discovery
Data in
Many Forms
Information Governance, Security and Business Continuity
12. AAP Capabilities
IBM Big Data Advanced Analytics
Platform (AAP) Architecture
Continuous Feed
Sources
Data Repositories
External
Data
3rd party
Visualize, explore, investigate, search
and report
High Volume
Data for
Historical
Analysis
Model
Creation
Capture
Changes
Event
Execution
Open API
Discovery Analytics
Take action on
analytics
Campaign Mgmt.
Pro-active
Customer
Experience
Management
Pro-active
Network Mgmt
Deploy Model
Policy
Mgmt
Real time Scoring
& Decision Mgmt.
Policy
Management
...
B
D
In Database Mining
Database Server
Batch
Data
A
Semi
Structured
Data
Analytics
Engine
UnStructured
E Data
Structured
Data
Hadoop Enterprise Data
Warehouse
Search, Pattern Matching, Quantitative, Qualitative
F
Insight
Advanced Analytics Platform
Create & Deliver
Smarter Services
G
High Performance
Unstructured Data
analysis
Actions
Deduplicate
Data Integration
ETL
F
C
Prediction / Policy Engine
Standardize
Identity
Resolution
Outcome
Optimization
E
Customer
Activities
Historical
Data
Models
Deploy Model
High Velocity
Social
Real-time scoring, classification,
detection and action
Streaming Engine
Network
Policies
Customer
Data
Model Based Predictive Analytics
Sense, Categorize,
Score,
Identify,
Count,
Decide
Align
Focus
Streaming Data
XDR
Application
& Usage
Data
B
D
Network
Topology
Data
High Performance Historical analysis
C
Network
Events
A
Transform Operations
Build Smarter
Networks
Customer Care
Reports &
Dashboards
Ad-hoc
Queries
Simulation
Marketing
Reports
Network
Planning
Dashboards
...
NOC/SOC
Geo/Sem
antic
Mapping
Information
Interaction
Users
Personalize Customer
Engagements
G
13. AAP Capabilities
IBM Big Data Advanced Analytics
Platform (AAP) Architecture
Continuous Feed
Sources
Data Repositories
External
Data
3rd party
F
G
High Performance
Unstructured Data
analysis
Discovery Analytics
Take action on
analytics
Customer
Activities
Event
Execution
Streaming Engine
Historical
Data
Models
Deploy Model
High Velocity
Social
Visualize, explore, investigate, search
and report
Sense, Categorize,
Score,
Identify,
Count,
Decide
Align
Focus
Streaming Data
Network
Policies
Customer
Data
Model Based Predictive Analytics
Real-time scoring, classification,
detection and action
E
InfoSphere Streams
XDR
Application
& Usage
Data
B
D
Network
Topology
Data
High Performance Historical analysis
C
Network
Events
A
High Volume
DataSPSS
for
Historical
Analysis
Model
Creation
Capture
Changes
BPM
WODM, Optim
Pro-active
Network Mgmt
Deploy Model
Policy
Mgmt
Real time Scoring
& Decision Mgmt.
WODM
B
In Database Mining
Database Server
Batch
Data
PDA
Semi
A
Structured
Data
Analytics
Engine
UnStructured
Structured
Data
Data
E InfoSphere
PDOA
BigInsights
Hadoop Enterprise Data
Warehouse
Search, Pattern
InfoSphere
Social Media Matching, Quantitative, Qualitative
F
Insight
Data Explorer
Analytics
Advanced Analytics Platform
Create & Deliver
Smarter Services
Pro-active
Customer
Experience
Management
Policy
Management
...
Actions
Deduplicate
Data Integration
ETL
Open API
C
Prediction / Policy Engine
Data Stage
Quality Stage
Standardize
MDM
Identity
Resolution
Outcome
Optimization
IBM
(Unica)
Campaign Mgmt.
Campaign
Transform Operations
Build Smarter
Networks
D
Cognos
Customer Care
Reports &
Dashboards
Ad-hoc
Queries
SPSS
Simulation
Reports
Dashboards
Marketing
Network
Planning
...
NOC/SOC
Geo/Sem
antic
Mapping
Information
Interaction
Users
Personalize Customer
Engagements
G
14. AAP Capabilities
Capabilities Overview
Capability
Streaming Engine
Prediction /
Policy Engine
Database
Server
Insight
Information
Interaction
Capability Description
ď§ Align diverse streams of data, identify customers, align to IDs, sense data importance
ď§ Categorize incoming data, use window counts to aggregate atomic data or threshold vioilations,
focus attention on monitored situations abstracted from raw events
ď§ Use scoring models developed by prediction engine to score observations, activities, customers,
etc. in real time
ď§ Make data ready for execution of events â e.g., designing campaign messages based on
information available.
ď§ Includes TEDA and geo-spatial accelerators
ď§
ď§
ď§
ď§
ď§
Create models using historical data sources
Optimize outcomes by promoting best model for a particular treatment (Champion / Challenger)
Manage policies associated with decisions â e.g., WODM decision rules, Optim data policies, etc.
Includes SPSS Deployment Server
Includes SPSS location analytics
ď§
ď§
ď§
ď§
Provide capabilities for storage of structured, unstructured and semi-structured data
Provide capabilities for analytics using DB functions (e.g., SPSS model development)
Provide capabilities for data archival using archival policies
Includes Optim / DS for archival policy execution
ď§ Deep analysis of consumer behavior is performed to mine data for model creation
ď§ Includes unstructured search, pattern matching using arbitrarily defined patterns, qualitative
analytics, quantification of data (e.g., sentiment analysis)
ď§ Includes Big Insights accelerators
ď§ Perform Ad hoc queries, standard reports, dash board
ď§ Run simulation models, what-if analysis
ď§ Geo-spatial and semantic viewing of data
15. Content
⢠Use cases to support Business Architecture
⢠Components to support Application Architecture
⢠Data Integration
⢠Privacy Management & Archiving
⢠Location & Lifestyle Analytics
⢠Adaptive Analytics
⢠Momentum and Conclusions
16. Mature Organizations are Looking for Instantaneous
Insight from Data
Speed to insight
Respondents were asked how quickly business users
require data to be available for analysis or within
processes. Box placement reflects the prevalence of
that requirements within each a stage.
Total respondents n = 973
16
17. Stream Computing Represents a Paradigm Shift
Traditional Computing
Stream Computing
Historical fact finding
Current fact finding
Find and analyze information stored on disk
Analyze data in motion â before it is stored
Batch paradigm, pull model
Low latency paradigm, push model
Query-driven: submits queries to static data
Data driven â bring data to the analytics
Real-time
Analytics
17
18. Massively scalable stream analytics
Deployments
Linear Scalability
⢠Clustered deployments â
unlimited scalability
Source
Adapters
Automated Deployment
⢠Automatically optimize
operator deployment
across nodes
Performance Optimization
⢠Parallel & pipeline
operations
⢠Efficient multi-threading
Analytics on Streaming Data
⢠Analytic accelerators for a
variety of data types
⢠Optimized for real-time
performance
18
Analytic
Operators
Sink
Adapters
Streams Studio IDE
Automated and
Optimized
Deployment
Streaming Data
Sources
Streams Runtime
Visualization
19. Big Data in Real Time with InfoSphere Streams
Filter / Sample
Modify
Analyze
Fuse
Classify
Score
19
Windowed
Aggregates
Annotate
20. AAP Capabilities
IBM Big Data Advanced Analytics
Platform (AAP) Architecture
Continuous Feed
Sources
Data Repositories
External
Data
3rd party
F
G
High Performance
Unstructured Data
analysis
Discovery Analytics
Take action on
analytics
Customer
Activities
Event
Execution
Streaming Engine
Historical
Data
Models
Deploy Model
High Velocity
Social
Visualize, explore, investigate, search
and report
Sense, Categorize,
Score,
Identify,
Count,
Decide
Align
Focus
Streaming Data
Network
Policies
Customer
Data
Model Based Predictive Analytics
Real-time scoring, classification,
detection and action
E
InfoSphere Streams
XDR
Application
& Usage
Data
B
D
Network
Topology
Data
High Performance Historical analysis
C
Network
Events
A
High Volume
DataSPSS
for
Historical
Analysis
Model
Creation
Capture
Changes
BPM
WODM, Optim
Pro-active
Network Mgmt
Deploy Model
Policy
Mgmt
Real time Scoring
& Decision Mgmt.
WODM
B
In Database Mining
Database Server
Batch
Data
PDA
Semi
A
Structured
Data
Analytics
Engine
UnStructured
Structured
Data
Data
E InfoSphere
PDOA
BigInsights
Hadoop Enterprise Data
Warehouse
Search, Pattern
InfoSphere
Social Media Matching, Quantitative, Qualitative
F
Insight
Data Explorer
Analytics
Advanced Analytics Platform
Create & Deliver
Smarter Services
Pro-active
Customer
Experience
Management
Policy
Management
...
Actions
Deduplicate
Data Integration
ETL
Open API
C
Prediction / Policy Engine
Standardize
Identity
Resolution
Outcome
Optimization
IBM
(Unica)
Campaign Mgmt.
Campaign
Transform Operations
Build Smarter
Networks
D
Cognos
Customer Care
Reports &
Dashboards
Ad-hoc
Queries
SPSS
Simulation
Reports
Dashboards
Marketing
Network
Planning
...
NOC/SOC
Geo/Sem
antic
Mapping
Information
Interaction
Users
Personalize Customer
Engagements
G
21. Content
⢠Use cases to support Business Architecture
⢠Components to support Application Architecture
⢠Data Integration
⢠Privacy Management & Archiving
⢠Location & Lifestyle Analytics
⢠Adaptive Analytics
⢠Momentum and Conclusions
22. What is Sensitive Data
Personally Sensitive
⢠Information that can be misused to harm a person in financial,
employment or social way. (Names, Social Security Number, Credit Card,
etc.)
Network Sensitive
⢠Information that can be misused to breech or disable critical
network communication (Circuit Identifiers, IP Addresses, etc.)
Corporate Sensitive
⢠Information that can misused to compromise the competitive
position of a company (Operational Metrics, etc.)
23. 6 steps that work together to achieve an acceptable and
manageable level of data security
Assess Risk
Audit
Define process
Processes &
Information assets
Manage
Implement
Controls
24. Data masking requires a combination of
process, templates and tools
Our approach brings together data masking infrastructure using DataStage and
ProfileStage, combining with Masking on Demand plug-in using Optim
technology.
Reusable Processes
Identify
Select
Verify
Implement
Validate
Templates
Masking Utilities
Data Definitions
- Incremental Autogen
- Swap
- Relational Group Swap
- String Replacement
- Universal Random
- Customer ID
- Name
- Address
- Credit Card No
- Social Sec No
- Etc.
Tools
InfoSphere Analyzer
Optim, DataStage
25. AAP Capabilities
IBM Big Data Advanced Analytics
Platform (AAP) Architecture
Continuous Feed
Sources
Data Repositories
External
Data
3rd party
F
G
High Performance
Unstructured Data
analysis
Discovery Analytics
Take action on
analytics
Customer
Activities
Event
Execution
Streaming Engine
Historical
Data
Models
Deploy Model
High Velocity
Social
Visualize, explore, investigate, search
and report
Sense, Categorize,
Score,
Identify,
Count,
Decide
Align
Focus
Streaming Data
Network
Policies
Customer
Data
Model Based Predictive Analytics
Real-time scoring, classification,
detection and action
E
InfoSphere Streams
XDR
Application
& Usage
Data
B
D
Network
Topology
Data
High Performance Historical analysis
C
Network
Events
A
High Volume
DataSPSS
for
Historical
Analysis
Model
Creation
Capture
Changes
BPM
WODM, Optim
Pro-active
Network Mgmt
Deploy Model
Policy
Mgmt
Real time Scoring
& Decision Mgmt.
WODM
B
In Database Mining
Database Server
Batch
Data
PDA
Semi
A
Structured
Data
Analytics
Engine
UnStructured
Structured
Data
Data
E InfoSphere
PDOA
BigInsights
Hadoop Enterprise Data
Warehouse
Search, Pattern
InfoSphere
Social Media Matching, Quantitative, Qualitative
F
Insight
Data Explorer
Analytics
Advanced Analytics Platform
Create & Deliver
Smarter Services
Pro-active
Customer
Experience
Management
Policy
Management
...
Actions
Deduplicate
Data Integration
ETL
Open API
C
Prediction / Policy Engine
Standardize
Identity
Resolution
Outcome
Optimization
IBM
(Unica)
Campaign Mgmt.
Campaign
Transform Operations
Build Smarter
Networks
D
Cognos
Customer Care
Reports &
Dashboards
Ad-hoc
Queries
SPSS
Simulation
Reports
Dashboards
Marketing
Network
Planning
...
NOC/SOC
Geo/Sem
antic
Mapping
Information
Interaction
Users
Personalize Customer
Engagements
G
26. Content
⢠Use cases to support Business Architecture
⢠Components to support Application Architecture
⢠Data Integration
⢠Privacy Management & Archiving
⢠Location & Lifestyle Analytics
⢠Adaptive Analytics
⢠Momentum and Conclusions
27. Buddies, Hangouts, Globtrotters
10 Top Hangouts
Areas of mobility analytics
ďŽ Individual Lifestyle and Usage profiles
ďŽ Popular Locations with specific profiles
ďŽ Who are the Buddies
ďŽ Predicting where people go
Who Are You?
Homebody
Daily Grinder
Delivering the Goods
Globetrotter
Sofa Surfer
Mobile ID
Buddy Rank
2702
1
1256
2
8786
3
4792
4
8950
5
Š 2012 IBM Corporation
28. What are Profiles
⢠Lifestyle Profiles are defined by marketing analysts for specific
use cases or marketing programs
⢠Usage Profiles are created using data mining algorithms and
define how a person uses services during the day
⢠Location Affinity is created with algorithms and determines
preferred locations for individuals throughout the day and
week
⢠Together these uniquely define a person with relation to how
the retailer or marketer might want to market to them
29. Creating Groups of Mobility Profiles Enables
Better Prediction for Certain Groups
ďŹ
profiles breakdown like this
ďŹ
Homebody, doesn't visit too many unique locations
ďŹ
Daily Grinder, back and forth to work, quiet weekends, makes
stops along the way
ďŹ
Norm Peterson, inside the lines, no deviations
ďŹ
Delivering the goods, no predictable patterns, many different
locales during the day
ďŹ
Globe Trotter, either not in town, or keeps their phone turned off
ďŹ
Rover Wanderer, spends evenings at various location (sofa
surfers www.couchsurfing.org)
ďŹ
âOtherâ, is a group hard to categorize
30. By Profile, when is it easy or difficult to predict
where they will be?
Profile
Day
Time
Predictability
Daily Grinder
Thursday
Dinner
Highest
Daily Grinder
Friday
Afternoon
Lowest
Homebody
Saturday
Night
Highest
Homebody
Wednesday
Morning
Lowest
These are the 2 most predictable profiles, yet there is diversity in their predictability.
To best communicate with Daily Grinders, contact them on Thursday Afternoons just before dinner
31. Preferred Locations of by profile type at
Lunchtime Weekdays (Central Stockholm)
Daily
Grinders
Night
Shifters
Delivering
the Goods
32. What analysis is available (Anonymous Data)
From the mobility profiles, summarized, anonymous analysis is
available
ďŹ
Summarized to ensure anonymity, analysis of popular locations
by time of day and profile of subscribers is possible
ďŹ
ďŹ
ďŹ
For retailers this information can help understand what types
of people are nearby at lunch time
What types of people prefer which areas. Some obvious
results are Globe Trotters go to airports, Daily Grinders go to
office buildings. Other non-obvious results show up also.
Are there predictable patterns that we can use to target
certain groups in the future?
33. What Makes this Possible?
ďŹ
ďŹ
Using the power of Netezza and modeling capabilities of SPSS we
can literally throw all the data at data mining algorithms and create
discrete clusters of subscribers by activity, mobility
Apply the data mining outputs to the entire subscriber base by
creating detailed specific analyses for each subscriber refined by the
mobility profiles
34. Content
⢠Use cases to support Business Architecture
⢠Components to support Application Architecture
⢠Data Integration
⢠Privacy Management & Archiving
⢠Location & Lifestyle Analytics
⢠Adaptive Analytics
⢠Momentum and Conclusions
36. Adaptive Analytics
⢠Collaboration across tools
⢠SPSS and iLOG to manage models and rules
⢠PDA to do query processing for the models
⢠Streams to run the model
⢠PMML to flow models from SPSS / iLOG to Streams
37. Content
⢠Use cases to support Business Architecture
⢠Components to support Application Architecture
⢠Data Integration
⢠Privacy Management & Archiving
⢠Location & Lifestyle Analytics
⢠Adaptive Analytics
⢠Momentum and Conclusions
38. Marketing Assets
Resource
Link
IBM Big Data Hub â Telco Home
Page
http://www-01.ibm.com/software/data/bigdata/industrytelco.html
IBM Big Data Hub Cross-industry
http://www.ibmbigdatahub.com/
Light Reading Webinar â âBig Data
dramatically changes the Telco
Game Planâ
http://www.lightreading.com/webinar.asp?webinar_id=300
92&webinar_promo=1000000332
Big Data Analytics (e-book)
http://ibm.co/Zw0jRW
Big Data Analytics for
Communications Service
Providers (whitepaper)
http://bitly.com/RJHbhj
Telco Industry Blog on IBM Big
Data Hub (Author - Gaurav
Deshpande)
http://www.ibmbigdatahub.com/blog/author/gauravdeshpande
Videos
http://www.youtube.com/watch?v=FIUFYyz03u8
http://www.youtube.com/watch?v=eg8KSLAZ2HM
http://pro.gigaom.com/webinars/netezza-making-bigdata-analytics-pay/
http://youtu.be/bdJu1Pt374g
39. IBM Big Data / Advanced Analytics Value Proposition
All Telco Data
Combine Network Data (usage, performance,
capacity), Billing Call Detail Records, Subscriber,
Channel, Policy, Device, Social etc.
At Scale
Ability to manage the stored Petabytes of data and
incoming billions of records per day
At Speed of
Business
Ability to process data and analytics in real time and
close to point of origination to support emerging use
cases such as Location Based Services (LBS) and
Machine to Machine (M2M)
Only IBM
Only IBM can deliver the complete end to end
technology and skills to capture quickly the new ERA
value of Telco Big Data
40. Communities
⢠On-line communities, User Groups, Technical Forums, Blogs, Social
networks, and more
o Find the community that interests you âŚ
⢠Information Management bit.ly/InfoMgmtCommunity
⢠Business Analytics bit.ly/AnalyticsCommunity
⢠Enterprise Content Management bit.ly/ECMCommunity
⢠IBM Champions
o Recognizing individuals who have made the most outstanding contributions to
Information Management, Business Analytics, and Enterprise Content
Management communities
â˘
ibm.com/champion
41. Thank You
Your feedback is important!
⢠Access the Conference Agenda Builder to
complete your session surveys
o Any web or mobile browser at
http://iod13surveys.com/surveys.html
o Any Agenda Builder kiosk onsite