SlideShare a Scribd company logo
AI in Telecom
How artificial intelligence is reshaping
the vision of telco industry
Gabriele Randelli
May 18th, 2018
Once upon a time in a telco operator…
2
- Traffic Volume
- Infrastructure as asset
- Customer-agnostic
- Data-agnostic
… there was an intruder
3
- Service oriented
- No infrastructure
- Customer-centric
- Data eager
Over-the-top (OTT) Players
4
OTTs
scrape out
44% of revenues
 No network infrastructure costs
 Customer-centric
 Leverage on data insights
 Low return from investment
 Customer-agnostic
 Content-agnostic
OTTs
market value
seven times
bigger than CSPs
Network costs vs revenues
5
US$354 billion into maintaining, building
and upgrading networks in 2014
Towards a subscriber-centric paradigm
6
AI
AI-assisted customer service
Next Best Action
Predictive Maintenance
Churn/Traffic PredictionNetwork
Anomaly Detection
Content Usage Trends
Fraud Detection
Customer
Profiling
Self-healing
Networks
Intelligent Edge
IoT & Edge
Converge data sources
(voice, data, fixed,
mobile, sensors,
billing, CRM,
network)
Automate
network processes
(zero-touch)
Customer-centric
services
Generate
new revenue
streams
Enable
AI-based
services
AI models adopted in Telco
7
Prediction
Supervised: Artificial Neural Networks, Decision Trees learning, Regression Analysis,
Support Vector Machines, Naive Bayes
Customer Churn
Predictive Maintenance
Fraud Propensity
Traffic Peak Prediction
Problem Use Case Model
Anomaly
Detection
(Semi-)Supervised: one-class Support Vector Machine
Unsupervised: Auto-encoders, cluster analysis, self-organizing maps, k-means
Traffic Analysis
Behavior Analysis
Network Monitoring
Predictive Maintenance
Profiling
Supervised: Recurrent Neural Networks (RNN)
Unsupervised: Principal Component Analysis
Customer Profiling
Network Usage
Next Best Offer
Classification
Supervised: Artificial Neural Networks, Decision Trees, Logistic Regression, Support
Vector Machines
Customer Care
Failure Analysis
Content Classification
Spotlight on Deep Learning
Data Availability
- 2.5 exa-bytes
(1018) per day!!!
- Deep learning
performance scales
almost linear wrt.
data amount
Text here
Computation Power
- Deep learning is
eager for training
resources
- Telco data centers
embed thousands
of machines with
very fast
connection
Text here
Edge Computing
- 5G moves
intelligence at the
edge
- Deep learning
scales very well on
dedicated hardware
(e.g. GPU, TPU)
- Collaborative
learning techniques
- Mobile AI
frameworks
(TensorFlow Lite)
Text here
Online Model Training
- From batch
analysis to real-
time streaming
- AI models need to
re-adapt to
evolving patterns
- What yesterday
was anomalous…
today is not!
- Still a lot to do in
this area…
Text here
Unsupervised Learning
- Labeling datasets
is not feasible
- No training effort
- Anomaly detection
algorithms largely
adopted for traffic
analysis (e.g. Auto-
encoders)
8
AI-based Customer Care
• By 2020, 85% of all customer interactions will be handled
without a human agent
• Resolving customer service issues before they arise could
significantly lower customer churning rate
• Combination of AI, NLP, chat-bots
9
HOW
• Anticipate customer needs by continuously profiling user
behaviors (anomaly detection)
• Extract potential complaints published on social networks
(sentiment analysis)
• Correlate user complaints with detected network failures
(cluster analysis)
• Compare incoming problems to support cases already
evaluated (root cause analysis)
• Predict potential problems (time-series analysis)
Customized Marketing
10
• 79% of CMOs are planning to boost customer experience
with AI
• AI algorithms combine historic patterns and behaviors to
provide personalized offers for subscribers
HOW
• Extract enriched customer insights from multiple data
sources
• Predict the potential interest of each customer for
available offers (prediction and ranking)
• Automatic offering proposition (when, what, how)
• Feedback collection and model update (reinforcement
learning, incremental learning)
Self-healing Networks
11
• A UK mobile operator was recently fined £1.9 million for
a network design configuration that would have
compromised access to the 911 emergency service
• AI predicts future traffic peaks and load distribution for
automatic network scaling
• AI predicts potential network failure for automatic alarm
triggering and network re-configuration
• Combination of AI and network virtualization (NFV)
HOW
• Predict what will happen in the network (predictive
networks)
• Evaluate and guide in assessing the impact of the
prediction (prescriptive networks)
• Automatic action selection to mitigate the impact of a
predicted outcome (self-healing networks)
Thank you
Gabriele Randelli
gabriele.randelli@hpe.com

More Related Content

What's hot

Role of Generative AI in Utilities
Role of Generative AI in UtilitiesRole of Generative AI in Utilities
Role of Generative AI in Utilities
Sayonsom Chanda
 
Internet of Things (IoT) - We Are at the Tip of An Iceberg
Internet of Things (IoT) - We Are at the Tip of An IcebergInternet of Things (IoT) - We Are at the Tip of An Iceberg
Internet of Things (IoT) - We Are at the Tip of An Iceberg
Dr. Mazlan Abbas
 

What's hot (20)

Harry Surden - Artificial Intelligence and Law Overview
Harry Surden - Artificial Intelligence and Law OverviewHarry Surden - Artificial Intelligence and Law Overview
Harry Surden - Artificial Intelligence and Law Overview
 
Functionalities in AI Applications and Use Cases (OECD)
Functionalities in AI Applications and Use Cases (OECD)Functionalities in AI Applications and Use Cases (OECD)
Functionalities in AI Applications and Use Cases (OECD)
 
IoT for Healthcare
IoT for HealthcareIoT for Healthcare
IoT for Healthcare
 
Artificial Intelligence & Machine Learning on AWS
Artificial Intelligence & Machine Learning on AWS Artificial Intelligence & Machine Learning on AWS
Artificial Intelligence & Machine Learning on AWS
 
Generative AI Use cases for Enterprise - Second Session
Generative AI Use cases for Enterprise - Second SessionGenerative AI Use cases for Enterprise - Second Session
Generative AI Use cases for Enterprise - Second Session
 
Leveraging the Power of Conversational AI for ITSM
Leveraging the Power of Conversational AI for ITSMLeveraging the Power of Conversational AI for ITSM
Leveraging the Power of Conversational AI for ITSM
 
Artificial Intelligence for Business
Artificial Intelligence for BusinessArtificial Intelligence for Business
Artificial Intelligence for Business
 
Data Analytics for IoT
Data Analytics for IoT Data Analytics for IoT
Data Analytics for IoT
 
Responsible AI & Cybersecurity: A tale of two technology risks
Responsible AI & Cybersecurity: A tale of two technology risksResponsible AI & Cybersecurity: A tale of two technology risks
Responsible AI & Cybersecurity: A tale of two technology risks
 
Role of Generative AI in Utilities
Role of Generative AI in UtilitiesRole of Generative AI in Utilities
Role of Generative AI in Utilities
 
Iot data analytics
Iot data analyticsIot data analytics
Iot data analytics
 
AI in Business: Opportunities & Challenges
AI in Business: Opportunities & ChallengesAI in Business: Opportunities & Challenges
AI in Business: Opportunities & Challenges
 
Social Media Meets Artificial Intelligence
Social Media Meets Artificial IntelligenceSocial Media Meets Artificial Intelligence
Social Media Meets Artificial Intelligence
 
AI in Retail
AI in RetailAI in Retail
AI in Retail
 
Internet of Things (IoT) - We Are at the Tip of An Iceberg
Internet of Things (IoT) - We Are at the Tip of An IcebergInternet of Things (IoT) - We Are at the Tip of An Iceberg
Internet of Things (IoT) - We Are at the Tip of An Iceberg
 
AI FOR BUSINESS LEADERS
AI FOR BUSINESS LEADERSAI FOR BUSINESS LEADERS
AI FOR BUSINESS LEADERS
 
UTILITY OF AI
UTILITY OF AIUTILITY OF AI
UTILITY OF AI
 
An Introduction to Generative AI
An Introduction  to Generative AIAn Introduction  to Generative AI
An Introduction to Generative AI
 
Iot how it works
Iot   how it worksIot   how it works
Iot how it works
 
AI in Marketing: Guest lecture at Bournemouth university
AI in Marketing: Guest lecture at Bournemouth university  AI in Marketing: Guest lecture at Bournemouth university
AI in Marketing: Guest lecture at Bournemouth university
 

Similar to AI in Telecom: How artificial intelligence is reshaping the vision of telco industry. Gabriele Randelli, HPE

How AI and ML Can Optimize the Supply Chain.pdf
How AI and ML Can Optimize the Supply Chain.pdfHow AI and ML Can Optimize the Supply Chain.pdf
How AI and ML Can Optimize the Supply Chain.pdf
Global Sources
 

Similar to AI in Telecom: How artificial intelligence is reshaping the vision of telco industry. Gabriele Randelli, HPE (20)

AI and the Financial Service Segment
AI and the Financial Service SegmentAI and the Financial Service Segment
AI and the Financial Service Segment
 
Digital Servicing Using Artificial Intelligence
Digital Servicing Using Artificial IntelligenceDigital Servicing Using Artificial Intelligence
Digital Servicing Using Artificial Intelligence
 
AI and Data Science.pdf
AI and Data Science.pdfAI and Data Science.pdf
AI and Data Science.pdf
 
Welcome to the Cognitive Supply Chain
Welcome to the Cognitive Supply ChainWelcome to the Cognitive Supply Chain
Welcome to the Cognitive Supply Chain
 
M&A Trends in Telco Analytics
M&A Trends in Telco AnalyticsM&A Trends in Telco Analytics
M&A Trends in Telco Analytics
 
Five FinTech Trends in 2018
Five FinTech Trends in 2018Five FinTech Trends in 2018
Five FinTech Trends in 2018
 
AI Applications in telecommunication industry
AI Applications in telecommunication industryAI Applications in telecommunication industry
AI Applications in telecommunication industry
 
Neo4j GraphTalk Copenhagen - Next Generation Solutions using Neo4j
Neo4j GraphTalk Copenhagen - Next Generation Solutions using Neo4j Neo4j GraphTalk Copenhagen - Next Generation Solutions using Neo4j
Neo4j GraphTalk Copenhagen - Next Generation Solutions using Neo4j
 
"From Big Data To Big Valuewith HPE Predictive Analytics & Machine Learning",...
"From Big Data To Big Valuewith HPE Predictive Analytics & Machine Learning",..."From Big Data To Big Valuewith HPE Predictive Analytics & Machine Learning",...
"From Big Data To Big Valuewith HPE Predictive Analytics & Machine Learning",...
 
Unlocking Business Value Using Data
Unlocking Business Value Using DataUnlocking Business Value Using Data
Unlocking Business Value Using Data
 
How AI and ML Can Optimize the Supply Chain.pdf
How AI and ML Can Optimize the Supply Chain.pdfHow AI and ML Can Optimize the Supply Chain.pdf
How AI and ML Can Optimize the Supply Chain.pdf
 
AI applications
AI applicationsAI applications
AI applications
 
Application of Artificial Intelligence
Application of Artificial IntelligenceApplication of Artificial Intelligence
Application of Artificial Intelligence
 
accelerating change AM Pres 2016
accelerating change AM Pres 2016accelerating change AM Pres 2016
accelerating change AM Pres 2016
 
Bi PowerPoint Presentation Slides
Bi PowerPoint Presentation SlidesBi PowerPoint Presentation Slides
Bi PowerPoint Presentation Slides
 
Big data in telecom
Big data in telecomBig data in telecom
Big data in telecom
 
Evolution of AI ML Solutions - A Review of Past and Future Impact.pdf
Evolution of AI ML Solutions - A Review of Past and Future Impact.pdfEvolution of AI ML Solutions - A Review of Past and Future Impact.pdf
Evolution of AI ML Solutions - A Review of Past and Future Impact.pdf
 
AI for optimizing customer journeys in online betting
AI for optimizing customer journeys in online bettingAI for optimizing customer journeys in online betting
AI for optimizing customer journeys in online betting
 
Credit Card Fraud Detection project.pptx
Credit Card Fraud Detection project.pptxCredit Card Fraud Detection project.pptx
Credit Card Fraud Detection project.pptx
 
AI in Insurance: How to Automate Insurance Claim Processing with Machine Lear...
AI in Insurance: How to Automate Insurance Claim Processing with Machine Lear...AI in Insurance: How to Automate Insurance Claim Processing with Machine Lear...
AI in Insurance: How to Automate Insurance Claim Processing with Machine Lear...
 

More from Data Driven Innovation

More from Data Driven Innovation (20)

Integrazione della mobilità elettrica nei sistemi urbani (Stefano Carrese, Un...
Integrazione della mobilità elettrica nei sistemi urbani (Stefano Carrese, Un...Integrazione della mobilità elettrica nei sistemi urbani (Stefano Carrese, Un...
Integrazione della mobilità elettrica nei sistemi urbani (Stefano Carrese, Un...
 
La statistica ufficiale e i trasporti marittimi nell'era dei big data (Vincen...
La statistica ufficiale e i trasporti marittimi nell'era dei big data (Vincen...La statistica ufficiale e i trasporti marittimi nell'era dei big data (Vincen...
La statistica ufficiale e i trasporti marittimi nell'era dei big data (Vincen...
 
How can we realize the Mobility as a Service (Maas) (Andrea Paletti, London S...
How can we realize the Mobility as a Service (Maas) (Andrea Paletti, London S...How can we realize the Mobility as a Service (Maas) (Andrea Paletti, London S...
How can we realize the Mobility as a Service (Maas) (Andrea Paletti, London S...
 
Il DTC-Lazio e i dati del patrimonio culturale (Maria Prezioso, Università To...
Il DTC-Lazio e i dati del patrimonio culturale (Maria Prezioso, Università To...Il DTC-Lazio e i dati del patrimonio culturale (Maria Prezioso, Università To...
Il DTC-Lazio e i dati del patrimonio culturale (Maria Prezioso, Università To...
 
CHNet-DHLab: Servizi Cloud a supporto dei beni culturali (Fabio Proietti, INF...
CHNet-DHLab: Servizi Cloud a supporto dei beni culturali (Fabio Proietti, INF...CHNet-DHLab: Servizi Cloud a supporto dei beni culturali (Fabio Proietti, INF...
CHNet-DHLab: Servizi Cloud a supporto dei beni culturali (Fabio Proietti, INF...
 
Progetto EOSC-Pillar (Fulvio Galeazzi, GARR)
Progetto EOSC-Pillar (Fulvio Galeazzi, GARR)Progetto EOSC-Pillar (Fulvio Galeazzi, GARR)
Progetto EOSC-Pillar (Fulvio Galeazzi, GARR)
 
Una infrastruttura per l’accesso al patrimonio culturale: il Progetto del Por...
Una infrastruttura per l’accesso al patrimonio culturale: il Progetto del Por...Una infrastruttura per l’accesso al patrimonio culturale: il Progetto del Por...
Una infrastruttura per l’accesso al patrimonio culturale: il Progetto del Por...
 
Utilizzo dei Big data per l’analisi dei flussi veicolari e della mobilità (Ma...
Utilizzo dei Big data per l’analisi dei flussi veicolari e della mobilità (Ma...Utilizzo dei Big data per l’analisi dei flussi veicolari e della mobilità (Ma...
Utilizzo dei Big data per l’analisi dei flussi veicolari e della mobilità (Ma...
 
I dati personali nell'analisi comportamentale della mobilità di dipendenti e ...
I dati personali nell'analisi comportamentale della mobilità di dipendenti e ...I dati personali nell'analisi comportamentale della mobilità di dipendenti e ...
I dati personali nell'analisi comportamentale della mobilità di dipendenti e ...
 
Estrarre valore dai dati: tecnologie per ottimizzare la mobilità del futuro (...
Estrarre valore dai dati: tecnologie per ottimizzare la mobilità del futuro (...Estrarre valore dai dati: tecnologie per ottimizzare la mobilità del futuro (...
Estrarre valore dai dati: tecnologie per ottimizzare la mobilità del futuro (...
 
Le piattaforme dati per la mobilità nelle città italiane (Marco Mena, EY)
Le piattaforme dati per la mobilità nelle città italiane (Marco Mena, EY)Le piattaforme dati per la mobilità nelle città italiane (Marco Mena, EY)
Le piattaforme dati per la mobilità nelle città italiane (Marco Mena, EY)
 
WiseTown, un ecosistema di applicazioni e strumenti per migliorare la qualità...
WiseTown, un ecosistema di applicazioni e strumenti per migliorare la qualità...WiseTown, un ecosistema di applicazioni e strumenti per migliorare la qualità...
WiseTown, un ecosistema di applicazioni e strumenti per migliorare la qualità...
 
CityOpenSource as a civic tech tool (Ilaria Vitellio, CityOpenSource)
CityOpenSource as a civic tech tool (Ilaria Vitellio, CityOpenSource)CityOpenSource as a civic tech tool (Ilaria Vitellio, CityOpenSource)
CityOpenSource as a civic tech tool (Ilaria Vitellio, CityOpenSource)
 
Big Data Confederation: toward the local urban data market place (Renzo Taffa...
Big Data Confederation: toward the local urban data market place (Renzo Taffa...Big Data Confederation: toward the local urban data market place (Renzo Taffa...
Big Data Confederation: toward the local urban data market place (Renzo Taffa...
 
Making citizens the eyes of policy makers: a sweet spot for hybrid AI? (Danie...
Making citizens the eyes of policy makers: a sweet spot for hybrid AI? (Danie...Making citizens the eyes of policy makers: a sweet spot for hybrid AI? (Danie...
Making citizens the eyes of policy makers: a sweet spot for hybrid AI? (Danie...
 
Dall'Agenda Digitale alla Smart City: il percorso di Roma Capitale verso il D...
Dall'Agenda Digitale alla Smart City: il percorso di Roma Capitale verso il D...Dall'Agenda Digitale alla Smart City: il percorso di Roma Capitale verso il D...
Dall'Agenda Digitale alla Smart City: il percorso di Roma Capitale verso il D...
 
Reusing open data: how to make a difference (Vittorio Scarano, Università di ...
Reusing open data: how to make a difference (Vittorio Scarano, Università di ...Reusing open data: how to make a difference (Vittorio Scarano, Università di ...
Reusing open data: how to make a difference (Vittorio Scarano, Università di ...
 
Gestire i beni culturali con i big data (Sandro Stancampiano, Istat)
Gestire i beni culturali con i big data (Sandro Stancampiano, Istat)Gestire i beni culturali con i big data (Sandro Stancampiano, Istat)
Gestire i beni culturali con i big data (Sandro Stancampiano, Istat)
 
Data Governance: cos’è e perché è importante? (Elena Arista, Erwin)
Data Governance: cos’è e perché è importante? (Elena Arista, Erwin)Data Governance: cos’è e perché è importante? (Elena Arista, Erwin)
Data Governance: cos’è e perché è importante? (Elena Arista, Erwin)
 
Data driven economy: bastano i dati per avviare una start up? (Gabriele Anton...
Data driven economy: bastano i dati per avviare una start up? (Gabriele Anton...Data driven economy: bastano i dati per avviare una start up? (Gabriele Anton...
Data driven economy: bastano i dati per avviare una start up? (Gabriele Anton...
 

Recently uploaded

Empowering Data Analytics Ecosystem.pptx
Empowering Data Analytics Ecosystem.pptxEmpowering Data Analytics Ecosystem.pptx
Empowering Data Analytics Ecosystem.pptx
benishzehra469
 
Investigate & Recover / StarCompliance.io / Crypto_Crimes
Investigate & Recover / StarCompliance.io / Crypto_CrimesInvestigate & Recover / StarCompliance.io / Crypto_Crimes
Investigate & Recover / StarCompliance.io / Crypto_Crimes
StarCompliance.io
 
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
yhkoc
 
standardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghhstandardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghh
ArpitMalhotra16
 
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
ukgaet
 
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单
ewymefz
 
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
ewymefz
 
Introduction-to-Cybersecurit57hhfcbbcxxx
Introduction-to-Cybersecurit57hhfcbbcxxxIntroduction-to-Cybersecurit57hhfcbbcxxx
Introduction-to-Cybersecurit57hhfcbbcxxx
zahraomer517
 
Professional Data Engineer Certification Exam Guide  _  Learn  _  Google Clou...
Professional Data Engineer Certification Exam Guide  _  Learn  _  Google Clou...Professional Data Engineer Certification Exam Guide  _  Learn  _  Google Clou...
Professional Data Engineer Certification Exam Guide  _  Learn  _  Google Clou...
Domenico Conte
 
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单
ewymefz
 
一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单
ewymefz
 
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
vcaxypu
 
一比一原版(QU毕业证)皇后大学毕业证成绩单
一比一原版(QU毕业证)皇后大学毕业证成绩单一比一原版(QU毕业证)皇后大学毕业证成绩单
一比一原版(QU毕业证)皇后大学毕业证成绩单
enxupq
 

Recently uploaded (20)

Empowering Data Analytics Ecosystem.pptx
Empowering Data Analytics Ecosystem.pptxEmpowering Data Analytics Ecosystem.pptx
Empowering Data Analytics Ecosystem.pptx
 
Investigate & Recover / StarCompliance.io / Crypto_Crimes
Investigate & Recover / StarCompliance.io / Crypto_CrimesInvestigate & Recover / StarCompliance.io / Crypto_Crimes
Investigate & Recover / StarCompliance.io / Crypto_Crimes
 
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
 
Uber Ride Supply Demand Gap Analysis Report
Uber Ride Supply Demand Gap Analysis ReportUber Ride Supply Demand Gap Analysis Report
Uber Ride Supply Demand Gap Analysis Report
 
standardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghhstandardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghh
 
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
 
Using PDB Relocation to Move a Single PDB to Another Existing CDB
Using PDB Relocation to Move a Single PDB to Another Existing CDBUsing PDB Relocation to Move a Single PDB to Another Existing CDB
Using PDB Relocation to Move a Single PDB to Another Existing CDB
 
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单
 
Q1’2024 Update: MYCI’s Leap Year Rebound
Q1’2024 Update: MYCI’s Leap Year ReboundQ1’2024 Update: MYCI’s Leap Year Rebound
Q1’2024 Update: MYCI’s Leap Year Rebound
 
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
 
Webinar One View, Multiple Systems No-Code Integration of Salesforce and ERPs
Webinar One View, Multiple Systems No-Code Integration of Salesforce and ERPsWebinar One View, Multiple Systems No-Code Integration of Salesforce and ERPs
Webinar One View, Multiple Systems No-Code Integration of Salesforce and ERPs
 
Introduction-to-Cybersecurit57hhfcbbcxxx
Introduction-to-Cybersecurit57hhfcbbcxxxIntroduction-to-Cybersecurit57hhfcbbcxxx
Introduction-to-Cybersecurit57hhfcbbcxxx
 
Innovative Methods in Media and Communication Research by Sebastian Kubitschk...
Innovative Methods in Media and Communication Research by Sebastian Kubitschk...Innovative Methods in Media and Communication Research by Sebastian Kubitschk...
Innovative Methods in Media and Communication Research by Sebastian Kubitschk...
 
tapal brand analysis PPT slide for comptetive data
tapal brand analysis PPT slide for comptetive datatapal brand analysis PPT slide for comptetive data
tapal brand analysis PPT slide for comptetive data
 
Professional Data Engineer Certification Exam Guide  _  Learn  _  Google Clou...
Professional Data Engineer Certification Exam Guide  _  Learn  _  Google Clou...Professional Data Engineer Certification Exam Guide  _  Learn  _  Google Clou...
Professional Data Engineer Certification Exam Guide  _  Learn  _  Google Clou...
 
Criminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdfCriminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdf
 
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单
 
一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单
 
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
 
一比一原版(QU毕业证)皇后大学毕业证成绩单
一比一原版(QU毕业证)皇后大学毕业证成绩单一比一原版(QU毕业证)皇后大学毕业证成绩单
一比一原版(QU毕业证)皇后大学毕业证成绩单
 

AI in Telecom: How artificial intelligence is reshaping the vision of telco industry. Gabriele Randelli, HPE

  • 1. AI in Telecom How artificial intelligence is reshaping the vision of telco industry Gabriele Randelli May 18th, 2018
  • 2. Once upon a time in a telco operator… 2 - Traffic Volume - Infrastructure as asset - Customer-agnostic - Data-agnostic
  • 3. … there was an intruder 3 - Service oriented - No infrastructure - Customer-centric - Data eager
  • 4. Over-the-top (OTT) Players 4 OTTs scrape out 44% of revenues  No network infrastructure costs  Customer-centric  Leverage on data insights  Low return from investment  Customer-agnostic  Content-agnostic OTTs market value seven times bigger than CSPs
  • 5. Network costs vs revenues 5 US$354 billion into maintaining, building and upgrading networks in 2014
  • 6. Towards a subscriber-centric paradigm 6 AI AI-assisted customer service Next Best Action Predictive Maintenance Churn/Traffic PredictionNetwork Anomaly Detection Content Usage Trends Fraud Detection Customer Profiling Self-healing Networks Intelligent Edge IoT & Edge Converge data sources (voice, data, fixed, mobile, sensors, billing, CRM, network) Automate network processes (zero-touch) Customer-centric services Generate new revenue streams Enable AI-based services
  • 7. AI models adopted in Telco 7 Prediction Supervised: Artificial Neural Networks, Decision Trees learning, Regression Analysis, Support Vector Machines, Naive Bayes Customer Churn Predictive Maintenance Fraud Propensity Traffic Peak Prediction Problem Use Case Model Anomaly Detection (Semi-)Supervised: one-class Support Vector Machine Unsupervised: Auto-encoders, cluster analysis, self-organizing maps, k-means Traffic Analysis Behavior Analysis Network Monitoring Predictive Maintenance Profiling Supervised: Recurrent Neural Networks (RNN) Unsupervised: Principal Component Analysis Customer Profiling Network Usage Next Best Offer Classification Supervised: Artificial Neural Networks, Decision Trees, Logistic Regression, Support Vector Machines Customer Care Failure Analysis Content Classification
  • 8. Spotlight on Deep Learning Data Availability - 2.5 exa-bytes (1018) per day!!! - Deep learning performance scales almost linear wrt. data amount Text here Computation Power - Deep learning is eager for training resources - Telco data centers embed thousands of machines with very fast connection Text here Edge Computing - 5G moves intelligence at the edge - Deep learning scales very well on dedicated hardware (e.g. GPU, TPU) - Collaborative learning techniques - Mobile AI frameworks (TensorFlow Lite) Text here Online Model Training - From batch analysis to real- time streaming - AI models need to re-adapt to evolving patterns - What yesterday was anomalous… today is not! - Still a lot to do in this area… Text here Unsupervised Learning - Labeling datasets is not feasible - No training effort - Anomaly detection algorithms largely adopted for traffic analysis (e.g. Auto- encoders) 8
  • 9. AI-based Customer Care • By 2020, 85% of all customer interactions will be handled without a human agent • Resolving customer service issues before they arise could significantly lower customer churning rate • Combination of AI, NLP, chat-bots 9 HOW • Anticipate customer needs by continuously profiling user behaviors (anomaly detection) • Extract potential complaints published on social networks (sentiment analysis) • Correlate user complaints with detected network failures (cluster analysis) • Compare incoming problems to support cases already evaluated (root cause analysis) • Predict potential problems (time-series analysis)
  • 10. Customized Marketing 10 • 79% of CMOs are planning to boost customer experience with AI • AI algorithms combine historic patterns and behaviors to provide personalized offers for subscribers HOW • Extract enriched customer insights from multiple data sources • Predict the potential interest of each customer for available offers (prediction and ranking) • Automatic offering proposition (when, what, how) • Feedback collection and model update (reinforcement learning, incremental learning)
  • 11. Self-healing Networks 11 • A UK mobile operator was recently fined £1.9 million for a network design configuration that would have compromised access to the 911 emergency service • AI predicts future traffic peaks and load distribution for automatic network scaling • AI predicts potential network failure for automatic alarm triggering and network re-configuration • Combination of AI and network virtualization (NFV) HOW • Predict what will happen in the network (predictive networks) • Evaluate and guide in assessing the impact of the prediction (prescriptive networks) • Automatic action selection to mitigate the impact of a predicted outcome (self-healing networks)