4th SG13 Regional Workshop for Africa on
“Future Networks for a better Africa: IMT-2020,
Trust, Cloud Computing and Big Data”
(Accra, Ghana, 14-15 March 2016)
Big Data – The Analytic Vision
Abdallah Ajlani Ph.D.,
Principal Consultant, ERICSSON
[email protected] Byline
Outline
APPROACH TO BIG DATA
EEA USE CASES
INTEGRATION IN OOREDOO TN
Telecom Big Data Unique Challenges
FacebookRoaming
VIP Service
Device CareSubscriber TetheringSpeedVoice
IncidentChurnQoE Location
Coverage
How to interpret
GUMMEI BCCH IupsX2APkHz
RNTI DRX RTT Ic/No
QCI
HSDSCH-CC ISUPARQRABPHICHNBAP
ICIC RACH/FACH
RANAFQPSKCQI PSPRSCPS1APID
How to correlate
E2E
OSS/BSS
CONTENT
RADIO CORE NETWORK
REAL TIME INSIGHTS AND ACTIONS
Networks, SOC, Care, Telecom Data Models & Insights
Marketing
Subscriber Service
Closed loop
Analytics
application
? action, e.g. • Subscriber Profile • OTT usage
Self Care
• Service Usage • Service Profile &
• Lifecycle, CE index, CLV Sessions
Query
? Real-Time
• Location, mobility, • Service Level Index
Human TELECOM roaming… • Quality Indicators (S-
“data Big Data DATA KPIs)…
scientist” Store ? MODELS
AND Networ
Network Device
Raw Stream
INSIGHTS
Real-Time k
data analysis • Incidents and Root • Device Profile
Closed loop Cause • Tethering
action, e.g. Policy • Traffic, Load and
Control
• Device usage
Forecast
• Replacement patterns…
• Performance
• Radio, Core, Data
ACTIONABLE INSIGHTS FROM COMBINATION OF UNIQUE, END-TO-END EXPERTISE THAT
Center…
OFFLINE AND ONLINE DATA EMPOWERS REAL WORLD USE CASES
UNIQUE data modeling
Technical User Overall
Session QoE User
Network Perception of
per User Satisfaction
Performance Service Quality
Resource-KPIs Service-KPIs & Service Level Net Promoter
& Counters E2E session record Index (SLI) Score (NPS)
Took too long to start Accessibility
Video didn’t start Video Accessibility
Video stopped Video Access Time
Video/App crashed Retainability
Buffer time is too long Video Retainability
Video freezes often Integrity Resolve
Video quality is bad Video Freeze Rate Drive
Part of the video is lost Video Quality & ARPU
Retain
The Service kpi concept
How to measure Accessibility e.g.
service Video Accessibility
A/R/I For Video
experience? Video Access Time
Retainability e.g.
Video Retainability
Integrity e.g.
End-users Video Freeze Rate
Video Quality
Services & Apps
Identify Understand Act
Network
Understand the Why of issues
• Determine the most probable cause when an S-KPI has a
threshold violation using the Correlate Subscriber QoE with
Device, Radio and Core network Resource KPIs (R-KPIs) for
each session Device
“Individual
“Holistic” “Real Time”
Customer”
End-to-End Session Record (ESR) Subscriptio Coverage
n
Servic Locati Transp
User QoE Device Radio Core …
e on ort
PDP
Web Throughpu Subscriptio Content
App usage Handovers Cell load experience connectivit UE type Topology
t n type
y
Interferenc Video Service Service Service
QoE Coverage freeze providers Attach Roaming CRM data
e Catalog quality
CPU load Radio Drop/ Page Voice
bearer QoS class Load Charging Profile Settings
outage delays quality
Usage
Congestion
Probes ….. 2G
OSS/BSS
CONTENT Internet
NETWORK
ENB MME SGW PDN GW
Terminals
Service Level Index (SLI)
VoLTE Sessions
Voice / SMS Sessions
Web Browsing Sessions Service
Video Streaming Sessions Level Index
(SLI)
Objective Service-KPIs: Subjective Weight – Early
Video Streaming Adopter Weight – Family
Subjective Predictor of
Subjective Weight – Student
=
Customer
Video Start Time Satisfaction
Subjective Weight –
Professional
Video Image
X
Available for
Quality Every User,
Service Continuously
Incident Memory
Video Freeze SignificancX X Updated
e
Repetition Fading
Correlates with
Video
Net Promoter
Retainability
Score
SLI Correlation with NPS
Outline
APPROACH TO BIG DATA
EEA USE CASES
INTEGRATION
Expert analytics themes
8
OPERATIONAL & CUSTOMER
BUSINESS
BUSINESS EXPERIENCE
INNOVATION
EFFICIENCY & MARKETING
2 3 4 5 6 7
PROACTIVE EMPOWERED EXPERIENCE CUSTOMER INDUSTRY &
DATA
SERVICE CUSTOMER BASED JOURNEY SOCIETY
MONETIZATION
OPERATIONS CARE MARKETING OPTIMIZATION (IoT)
1 ANALYTICS PLATFORM & INSIGHTS
1
ANALYTICS PLATFORM & insights
FLEXIBILITY REDUCED COST
Flexible KPI Management Reduced TCO (HW footprint and 3PP license
cost)
Data Source Ingestion
Data Center Deployment
Micro-service architecture
Hadoop 2.0
CAPABILITY ADVANCED MODELS
Self Learning Rules
CLI - Cell Level
Streaming Analytics to provide near real-time Index
Cell 567340
insights CLI: 8.4
Nita Video CLI: 8.1
CEI - Customer
Journey
Actuation Logic Web CLI: 9.3
2
Proactive service operations
IMPROVED EFFICENCY IN OPERATIONS SERVICE QUALITY MANAGEMENT
• Customer-centric analysis
and added drill-down • Proactive / (Near) real-time
capability monitoring of Service
Quality / SLA’s
• Workflows and
functionalities (e.g. • Reduce handling time with
roaming, CSP Incidents, root cause and Impact
Drill-down to Incident analysis
Summary/List)
SESSION BROWSER VIP AND ENTERPRISE CUSTOMERS
• Rapid identification of root • Assure strict Enterprise
cause level Service SLAs
• Deep flow cross-protocol • E2E Actuations to
analysis optimize experience of
certain VIP and Enterprise
• Per subscriber control & customers.
user plane event browser
3
EMPOWERED CUSTOMER CARE
TIER 1 & TIER 2 IMPROVEMENTS INTELLIGENT SELF-CARE
• Further Improve Efficiency
of Tier-1 Customer Care • Reduce cost with self
Agents and Expand Use to care capabilities to
Tier-2+ Agents
manage complaints
• Improve out-of-box Most
Probable Causes and next • Intelligent self-
Best Actions service
recommendations
ROAMING ANALYTICS CHARGING & BILLING INSIGHTS
• Proactive monitoring of
Inbound Roaming to avoid • Enrich with per
Revenue Leakage
transaction data from
• Experience on Inbound/ call & account history
Outbound Roaming
• Find correlation
• Including input from UDM
between charging &
experience
4
Experience based marketing
SLI ENHANCEMENTS PRE-PAID RETENTION
• Calibration
• Identify pre-paid
Profit
Service Level Index Enhancements CLV
• Improved SLI Root customers to keep
Cause drilldown and start monitor
Loss
• SLI Validation
• Trigger action when
improvements with
Extend Customer Lifecycleusers at a critical
statistics and tracing
stage of their
lifecycle
ARPU OPTIMIZATION MOBILE BROADBAND BOOSTER
Profit
• Identify customers • Identify users at a
Profit
CLV CLV
holding back on their critical stage of their
spending lifecycle
Loss
Loss
• Trigger action when • Convert ad hoc data
Expand Customer Expand Customer
Lifecycle Value (CLV) user demand Lifecycle Value (CLV) users to a re-
increases occurring data
package
6
Data MONETIZATION
RETAIL CAMPAIGNS OPTIMIZATION SPECIAL EVENTS
• Allow operators to • Demograpic
monetize analysis
anonymized • Traffic patterns
subsciber insights and footfall
based on their analysis
interests. • Upsell / Crossell
• Footfall analysis
• Lead generation
LOCATION BASED NETWORK ANALYTICS CONTEXTUAL MARKETING
• Combine network • Real time context,
quality and location interests and
data and improve behavioural
network customer patterns to allow
experience B2B monetization
Analytics use cases
SoC: Proactive Service Operations SoC: VoLTE Analytics CC: Improve call resolution in customer ca
Marketing Analytics: SoC: Real-Time Enterprise SLA Assurance Marketing Analytics:
Dynamic Experience Management Customer Retention & Drive Spend
Outline
APPROACH TO BIG DATA
EEA USE CASES
INTEGRATION
ANALYTICS ARCHITECTURE
JMS Trouble ticket Operator’s 3PP Exposure
actuation** request** Map server* and Analytics
tools *
Web service
(Api’s)
Exposure and
Visualization Customer Service Executive Dynamic QoE Marketing
Care Views Operations Views Dashboard Management Views Analytics
Layer
Web application server
In memory
Online repository (GREENPLUM) Offline repository
Storage Layer data grids
(HADOOP)
SNCD Incident Esr Data Real time Subscriber
generator data Stream loaders Actuation Profiler and
Processing Layer loader
loader
Aggregator
analytics Sli calculation
PCRF
Reference data
CRM
Cell info Extended session records Real time event stream
Correlation Layer IMEI TAC
Billing Real Time Correlator
External Generic RNC / E/// GPEH E/// CTR E/// EBM Generic SGSN / E/// ctum Generic KPI GTP CDR IMS
Subscriber eNodeB If adapters adapters adapters MME Interface adapters Interface Probes Adapters Probes
data
Connection Layer
3G
UE O
S sgsn
rnc S
sgsn /
MME IM
4G
UE MSC
S
enb EMM
ggsn
Integration with OSS/BSS SUITE
3PP Exposure
TroubleTicketin and Analytics
tools
API for CRM GUI
CRM g
Self Care
Reference data
CRM Customer info
SLA
/
Cell topology (NIM) SLI billing
ETSI IMEI / TAC db
EEA
SMS
Notifications
NPS
Customer Surveys DB
expert analytics
summary
Award Winning Solution Productized Applications
Winner in the Mobile CEM category
CTIA 2015, Las
Vegas
Planning Sales&Marketing I&S
Operations Customer Care
Advanced Business Logic E2E Actuation
Subscrib
er Service
Closed
Device Networ Loop
Network
k SERVICE LEVEL INDEX Actions
Customer
Pre-packaged logic:
Unloc
- Data Models Resolve
k
- Service KPIs & Retain
ARPU
Real-Time
- Patented Data Correlation
- Machine Learning Insights
