SlideShare une entreprise Scribd logo
1  sur  17
The Social Effect: Predicting Telecom Customer Churn with Call Data Michael E. Driscoll, Ph.D. Principal, Founder February 16, 2010
Social Network Analysis with Telecom Data The following slides describe an initial project analyzing a N. American telecom’s call data on a dedicated analytics platform: We describe the analysis of a slice of a telecom’s call history data from several million customers in the several major North American markets. We demonstrate the performance gain achieved by having a dedicated analytics platform (computation of  millions of relationships from tens of billions of events, spanning tens of TB of data, in less than one hour) We show  that social network influence is a powerful predictor of customer churn:  subscribers who experience a Telecom cancellation in their frequent calling network are 2x more likely to cancel themselves. We highlight one outbreak of cancellations in a metropolitan call network from May-June 2009.
Challenge:  Customer Churn Acquisition Attrition
Key Data:  Call Detail Records A slice of several billion call detail records (CDRs) from several million subscribers drawn from three major North American markets, for May-August 2009.
Call Quality Analysis No Relationship Between Dropped Calls and Customer Churn No significant correlation found between: ,[object Object],library(ggplot2) qplot(Status, DroppedCalls,    data=CallHistory, geom="boxplot“) Box plot to shows log-normalized distributions of dropped call frequencies (drops per 100 calls) for 10k customers placed, faceted by active and cancelled subscribers.
What about social networks?
Social Network Analysis Network is Generated from Call History Data Call history logs were pulled from the Greenplum warehouse.  These were parsed and outgoing numbers were associated with subscription ids.  The result is a row of data for every caller-callee connection meeting a low threshold (> 1 call and > 60 s talk-time per month).  The majority are between Telecom customers and other carriers (or land-lines).
Our Analytics Workflow Three steps:  1.  Pull from DB, 2.  Analyze in R,  3.  Visualize in R + Graphviz
Our Tool:  The R Programming Language Download R at http://www.r-project.org/
Getting Call Data Into R for Analysis 	- from Files > Calls <- read.csv(“CallHistory.csv”,header=TRUE) 	  from Databases > con <- dbConnect(driver,user,password,host,dbname) > Calls <- dbSendQuery(con, “SELECT * FROM call_history”) 	  from the Web > con <- url('http://Telco.com/dump/CallHistory.csv') > Calls <- read.csv(con, header=TRUE) 	   from previous R objects > load(‘CallHistory.RData’)
Social Network Analysis Millions of edges analyzed in minutes Full analysis of a first-order outgoing call network for our slice (~ millions of customers, three months of call history) took less than one hour. This could be further improved with further parallelization of R code (currently SQL queries run parallel on Greenplum, R is run on master node).
Results:  People Have Small Call Networks (Three) The median size of a caller’s network is three,  while the mean size is five.
Results: Canceling Customers are 7x More Likely to be Linked Types of Callers (Nodes) active (A) cancelled (C) Types of Connections (Edges) A-A A-C or C-A C-C C-C edges are 7x more likely in call networks  than what is expected by chance
Results:  A Customer With a Canceller in Their Network  Churns at Twice the Rate Types of Connections (Edges) May C-A June C-C In essence, we are asking whether being connected to another canceller has any effect on one’s rate of cancellation.  It turns out that it does.    And if we only look at voluntary port-outs, we see that customers churn at 3x the rate.
From Data to Insights to Actions If we had known two customers’ calling networks… Could we have prevented four more from leaving?
The Emerging Analytics Stack Actions Apps  (Email, Ad Campaigns) Analytics (R, SPSS, SAS, SAP) Insights Big Data (HDFS or Parallel RDBMS)  Data
References Enhancing Customer Knowledge at Optus, Teradata Case-Study (September 2009). IBM’s Analytics Tapped to Predict, Prevent Churn.  Telephony Online (April 2009).   The Elements of Statistical Learning, Hastie, Tibshirani, Friedman.  Springer. (February 2009). Study Shows Obesity Can Be Contagious, Gina Kolata, The New York Times (July 25, 2007)  [great example of homophily] Contact Michael E. Driscoll, Ph.D. med@dataspora.com Follow @datasporaon Twitter

Contenu connexe

Tendances

Buy vs Build - Customer Data Platform (CDP) for Financial Services
Buy vs Build - Customer Data Platform (CDP) for Financial ServicesBuy vs Build - Customer Data Platform (CDP) for Financial Services
Buy vs Build - Customer Data Platform (CDP) for Financial ServicesLemnisk
 
Telecommunication Analysis (3 use-cases) with IBM watson analytics
Telecommunication Analysis (3 use-cases) with IBM watson analyticsTelecommunication Analysis (3 use-cases) with IBM watson analytics
Telecommunication Analysis (3 use-cases) with IBM watson analyticssheetal sharma
 
Big data analytics for telecom operators final use cases 0712-2014_prof_m erdas
Big data analytics for telecom operators final use cases 0712-2014_prof_m erdasBig data analytics for telecom operators final use cases 0712-2014_prof_m erdas
Big data analytics for telecom operators final use cases 0712-2014_prof_m erdasProf Dr Mehmed ERDAS
 
Big data 2017 final
Big data 2017   finalBig data 2017   final
Big data 2017 finalAmjid Ali
 
E-Business: Chapter 1: Intro to E-B
E-Business: Chapter 1: Intro to E-BE-Business: Chapter 1: Intro to E-B
E-Business: Chapter 1: Intro to E-BArry Arman
 
Telecom Churn Prediction Presentation
Telecom Churn Prediction PresentationTelecom Churn Prediction Presentation
Telecom Churn Prediction PresentationPinintiHarishReddy
 
Case 3.1 - Big data big rewards
Case 3.1 - Big data big rewardsCase 3.1 - Big data big rewards
Case 3.1 - Big data big rewardsniz73
 
Exercise solution of chapter1 of datawarehouse cs614(solution of exercise)
Exercise solution of chapter1 of datawarehouse cs614(solution of exercise)Exercise solution of chapter1 of datawarehouse cs614(solution of exercise)
Exercise solution of chapter1 of datawarehouse cs614(solution of exercise)AYESHA JAVED
 
Building the connected Supply Chain – how digital is transforming Asia-Pacific
Building the connected Supply Chain – how digital is transforming Asia-PacificBuilding the connected Supply Chain – how digital is transforming Asia-Pacific
Building the connected Supply Chain – how digital is transforming Asia-PacificOrange Business Services
 
How to win a machine learning competition pavel pleskov
How to win a machine learning competition   pavel pleskovHow to win a machine learning competition   pavel pleskov
How to win a machine learning competition pavel pleskovDataFest Tbilisi
 
Improving the customer experience using big data customer-centric measurement...
Improving the customer experience using big data customer-centric measurement...Improving the customer experience using big data customer-centric measurement...
Improving the customer experience using big data customer-centric measurement...Business Over Broadway
 
Customer Churn, A Data Science Use Case in Telecom
Customer Churn, A Data Science Use Case in TelecomCustomer Churn, A Data Science Use Case in Telecom
Customer Churn, A Data Science Use Case in TelecomChris Chen
 
A case study on churn analysis1
A case study on churn analysis1A case study on churn analysis1
A case study on churn analysis1Amit Kumar
 
B2B Customer Experience Case Study | Telecom Industry
B2B Customer Experience Case Study | Telecom IndustryB2B Customer Experience Case Study | Telecom Industry
B2B Customer Experience Case Study | Telecom IndustryIntense Technologies Limited
 
huawei company profile
huawei company profile  huawei company profile
huawei company profile ssuser220dc6
 
Unplanned analytics-led transformation
Unplanned analytics-led transformationUnplanned analytics-led transformation
Unplanned analytics-led transformationaccenture
 

Tendances (20)

Buy vs Build - Customer Data Platform (CDP) for Financial Services
Buy vs Build - Customer Data Platform (CDP) for Financial ServicesBuy vs Build - Customer Data Platform (CDP) for Financial Services
Buy vs Build - Customer Data Platform (CDP) for Financial Services
 
Telecommunication Analysis (3 use-cases) with IBM watson analytics
Telecommunication Analysis (3 use-cases) with IBM watson analyticsTelecommunication Analysis (3 use-cases) with IBM watson analytics
Telecommunication Analysis (3 use-cases) with IBM watson analytics
 
Big data analytics for telecom operators final use cases 0712-2014_prof_m erdas
Big data analytics for telecom operators final use cases 0712-2014_prof_m erdasBig data analytics for telecom operators final use cases 0712-2014_prof_m erdas
Big data analytics for telecom operators final use cases 0712-2014_prof_m erdas
 
Big data 2017 final
Big data 2017   finalBig data 2017   final
Big data 2017 final
 
E-Business: Chapter 1: Intro to E-B
E-Business: Chapter 1: Intro to E-BE-Business: Chapter 1: Intro to E-B
E-Business: Chapter 1: Intro to E-B
 
Telecom Churn Prediction Presentation
Telecom Churn Prediction PresentationTelecom Churn Prediction Presentation
Telecom Churn Prediction Presentation
 
Case 3.1 - Big data big rewards
Case 3.1 - Big data big rewardsCase 3.1 - Big data big rewards
Case 3.1 - Big data big rewards
 
Exercise solution of chapter1 of datawarehouse cs614(solution of exercise)
Exercise solution of chapter1 of datawarehouse cs614(solution of exercise)Exercise solution of chapter1 of datawarehouse cs614(solution of exercise)
Exercise solution of chapter1 of datawarehouse cs614(solution of exercise)
 
Building the connected Supply Chain – how digital is transforming Asia-Pacific
Building the connected Supply Chain – how digital is transforming Asia-PacificBuilding the connected Supply Chain – how digital is transforming Asia-Pacific
Building the connected Supply Chain – how digital is transforming Asia-Pacific
 
How to win a machine learning competition pavel pleskov
How to win a machine learning competition   pavel pleskovHow to win a machine learning competition   pavel pleskov
How to win a machine learning competition pavel pleskov
 
Improving the customer experience using big data customer-centric measurement...
Improving the customer experience using big data customer-centric measurement...Improving the customer experience using big data customer-centric measurement...
Improving the customer experience using big data customer-centric measurement...
 
Customer Churn, A Data Science Use Case in Telecom
Customer Churn, A Data Science Use Case in TelecomCustomer Churn, A Data Science Use Case in Telecom
Customer Churn, A Data Science Use Case in Telecom
 
Recruiter Investors Presentations 2022
Recruiter Investors Presentations 2022Recruiter Investors Presentations 2022
Recruiter Investors Presentations 2022
 
Data science
Data science Data science
Data science
 
Churn modelling
Churn modellingChurn modelling
Churn modelling
 
A case study on churn analysis1
A case study on churn analysis1A case study on churn analysis1
A case study on churn analysis1
 
B2B Customer Experience Case Study | Telecom Industry
B2B Customer Experience Case Study | Telecom IndustryB2B Customer Experience Case Study | Telecom Industry
B2B Customer Experience Case Study | Telecom Industry
 
huawei company profile
huawei company profile  huawei company profile
huawei company profile
 
Unplanned analytics-led transformation
Unplanned analytics-led transformationUnplanned analytics-led transformation
Unplanned analytics-led transformation
 
IOT report
IOT reportIOT report
IOT report
 

En vedette

Applying sonamine social network analysis to telecommunications marketing
Applying sonamine social network analysis to telecommunications marketingApplying sonamine social network analysis to telecommunications marketing
Applying sonamine social network analysis to telecommunications marketingSonamine
 
Subscriber Churn Prediction Model using Social Network Analysis In Telecommun...
Subscriber Churn Prediction Model using Social Network Analysis In Telecommun...Subscriber Churn Prediction Model using Social Network Analysis In Telecommun...
Subscriber Churn Prediction Model using Social Network Analysis In Telecommun...BAINIDA
 
Idiro Analytics - Identifying Families using Social Network Analysis and Big ...
Idiro Analytics - Identifying Families using Social Network Analysis and Big ...Idiro Analytics - Identifying Families using Social Network Analysis and Big ...
Idiro Analytics - Identifying Families using Social Network Analysis and Big ...Idiro Analytics
 
Idiro Analytics - What is Rotational Churn and how can we tackle it?
Idiro Analytics - What is Rotational Churn and how can we tackle it?Idiro Analytics - What is Rotational Churn and how can we tackle it?
Idiro Analytics - What is Rotational Churn and how can we tackle it?Idiro Analytics
 
Deriving economic value for CSPs with Big Data [read-only]
Deriving economic value for CSPs with Big Data [read-only]Deriving economic value for CSPs with Big Data [read-only]
Deriving economic value for CSPs with Big Data [read-only]Flytxt
 
Telco Churn Roi V3
Telco Churn Roi V3Telco Churn Roi V3
Telco Churn Roi V3hkaul
 
Idiro Analytics - Social Network Analysis for Online Gaming
Idiro Analytics - Social Network Analysis for Online GamingIdiro Analytics - Social Network Analysis for Online Gaming
Idiro Analytics - Social Network Analysis for Online GamingIdiro Analytics
 
Big Telco - Yousun Jeong
Big Telco - Yousun JeongBig Telco - Yousun Jeong
Big Telco - Yousun JeongSpark Summit
 
Idiro Analytics - Analytics & Big Data
Idiro Analytics - Analytics & Big DataIdiro Analytics - Analytics & Big Data
Idiro Analytics - Analytics & Big DataIdiro Analytics
 
Churn Analysis in Telecom Industry
Churn Analysis in Telecom IndustryChurn Analysis in Telecom Industry
Churn Analysis in Telecom IndustrySatyam Barsaiyan
 
Predicting churn in telco industry: machine learning approach - Marko Mitić
 Predicting churn in telco industry: machine learning approach - Marko Mitić Predicting churn in telco industry: machine learning approach - Marko Mitić
Predicting churn in telco industry: machine learning approach - Marko MitićInstitute of Contemporary Sciences
 
Decide on technology stack & data architecture
Decide on technology stack & data architectureDecide on technology stack & data architecture
Decide on technology stack & data architectureSV.CO
 
Leveraging Kafka for Big Data in Real Time Bidding, Analytics, ML & Campaign ...
Leveraging Kafka for Big Data in Real Time Bidding, Analytics, ML & Campaign ...Leveraging Kafka for Big Data in Real Time Bidding, Analytics, ML & Campaign ...
Leveraging Kafka for Big Data in Real Time Bidding, Analytics, ML & Campaign ...Helena Edelson
 
Social network analysis & Big Data - Telecommunications and more
Social network analysis & Big Data - Telecommunications and moreSocial network analysis & Big Data - Telecommunications and more
Social network analysis & Big Data - Telecommunications and moreWael Elrifai
 
How to use your CRM for upselling and cross-selling
How to use your CRM for upselling and cross-sellingHow to use your CRM for upselling and cross-selling
How to use your CRM for upselling and cross-sellingRedspire Ltd
 
Big Data: Social Network Analysis
Big Data: Social Network AnalysisBig Data: Social Network Analysis
Big Data: Social Network AnalysisMichel Bruley
 
Big Data Analytics : A Social Network Approach
Big Data Analytics : A Social Network ApproachBig Data Analytics : A Social Network Approach
Big Data Analytics : A Social Network ApproachAndry Alamsyah
 

En vedette (17)

Applying sonamine social network analysis to telecommunications marketing
Applying sonamine social network analysis to telecommunications marketingApplying sonamine social network analysis to telecommunications marketing
Applying sonamine social network analysis to telecommunications marketing
 
Subscriber Churn Prediction Model using Social Network Analysis In Telecommun...
Subscriber Churn Prediction Model using Social Network Analysis In Telecommun...Subscriber Churn Prediction Model using Social Network Analysis In Telecommun...
Subscriber Churn Prediction Model using Social Network Analysis In Telecommun...
 
Idiro Analytics - Identifying Families using Social Network Analysis and Big ...
Idiro Analytics - Identifying Families using Social Network Analysis and Big ...Idiro Analytics - Identifying Families using Social Network Analysis and Big ...
Idiro Analytics - Identifying Families using Social Network Analysis and Big ...
 
Idiro Analytics - What is Rotational Churn and how can we tackle it?
Idiro Analytics - What is Rotational Churn and how can we tackle it?Idiro Analytics - What is Rotational Churn and how can we tackle it?
Idiro Analytics - What is Rotational Churn and how can we tackle it?
 
Deriving economic value for CSPs with Big Data [read-only]
Deriving economic value for CSPs with Big Data [read-only]Deriving economic value for CSPs with Big Data [read-only]
Deriving economic value for CSPs with Big Data [read-only]
 
Telco Churn Roi V3
Telco Churn Roi V3Telco Churn Roi V3
Telco Churn Roi V3
 
Idiro Analytics - Social Network Analysis for Online Gaming
Idiro Analytics - Social Network Analysis for Online GamingIdiro Analytics - Social Network Analysis for Online Gaming
Idiro Analytics - Social Network Analysis for Online Gaming
 
Big Telco - Yousun Jeong
Big Telco - Yousun JeongBig Telco - Yousun Jeong
Big Telco - Yousun Jeong
 
Idiro Analytics - Analytics & Big Data
Idiro Analytics - Analytics & Big DataIdiro Analytics - Analytics & Big Data
Idiro Analytics - Analytics & Big Data
 
Churn Analysis in Telecom Industry
Churn Analysis in Telecom IndustryChurn Analysis in Telecom Industry
Churn Analysis in Telecom Industry
 
Predicting churn in telco industry: machine learning approach - Marko Mitić
 Predicting churn in telco industry: machine learning approach - Marko Mitić Predicting churn in telco industry: machine learning approach - Marko Mitić
Predicting churn in telco industry: machine learning approach - Marko Mitić
 
Decide on technology stack & data architecture
Decide on technology stack & data architectureDecide on technology stack & data architecture
Decide on technology stack & data architecture
 
Leveraging Kafka for Big Data in Real Time Bidding, Analytics, ML & Campaign ...
Leveraging Kafka for Big Data in Real Time Bidding, Analytics, ML & Campaign ...Leveraging Kafka for Big Data in Real Time Bidding, Analytics, ML & Campaign ...
Leveraging Kafka for Big Data in Real Time Bidding, Analytics, ML & Campaign ...
 
Social network analysis & Big Data - Telecommunications and more
Social network analysis & Big Data - Telecommunications and moreSocial network analysis & Big Data - Telecommunications and more
Social network analysis & Big Data - Telecommunications and more
 
How to use your CRM for upselling and cross-selling
How to use your CRM for upselling and cross-sellingHow to use your CRM for upselling and cross-selling
How to use your CRM for upselling and cross-selling
 
Big Data: Social Network Analysis
Big Data: Social Network AnalysisBig Data: Social Network Analysis
Big Data: Social Network Analysis
 
Big Data Analytics : A Social Network Approach
Big Data Analytics : A Social Network ApproachBig Data Analytics : A Social Network Approach
Big Data Analytics : A Social Network Approach
 

Similaire à Social Network Analysis for Telecoms

Meetup prague 201811_v01
Meetup prague 201811_v01Meetup prague 201811_v01
Meetup prague 201811_v01Milos Molnar
 
AI Applications in telecommunication industry
AI Applications in telecommunication industryAI Applications in telecommunication industry
AI Applications in telecommunication industryAtefe Shahrokhi
 
Proposal for System Analysis and Desing
Proposal for System Analysis and DesingProposal for System Analysis and Desing
Proposal for System Analysis and DesingMd Khaza Main Uddin
 
Market basket predictive_model
Market basket predictive_modelMarket basket predictive_model
Market basket predictive_modelFatima Khalid
 
The data traffic and data warehouses store managing and controlling
The data traffic and data warehouses store managing and controllingThe data traffic and data warehouses store managing and controlling
The data traffic and data warehouses store managing and controllingAlexander Decker
 
The Spring 2018 Undergraduate Symposium Poster
The Spring 2018 Undergraduate Symposium PosterThe Spring 2018 Undergraduate Symposium Poster
The Spring 2018 Undergraduate Symposium PosterTanner Massahos
 
IEEE 2015 C# Projects
IEEE 2015 C# ProjectsIEEE 2015 C# Projects
IEEE 2015 C# ProjectsVijay Karan
 
IRJET- Competitive Analysis of Attacks on Social Media
IRJET-  	 Competitive Analysis of Attacks on Social MediaIRJET-  	 Competitive Analysis of Attacks on Social Media
IRJET- Competitive Analysis of Attacks on Social MediaIRJET Journal
 
IEEE 2015 C# Projects
IEEE 2015 C# ProjectsIEEE 2015 C# Projects
IEEE 2015 C# ProjectsVijay Karan
 
[Big] Data For Marketers: Targeting the Right Market
[Big] Data For Marketers: Targeting the Right Market[Big] Data For Marketers: Targeting the Right Market
[Big] Data For Marketers: Targeting the Right MarketPanji Winata
 
Customer segmentation for a mobile telecommunications company based on servic...
Customer segmentation for a mobile telecommunications company based on servic...Customer segmentation for a mobile telecommunications company based on servic...
Customer segmentation for a mobile telecommunications company based on servic...Shohin Aheleroff
 
BIG DATA ANALYTICS FOR USER-ACTIVITY ANALYSIS AND USER-ANOMALY DETECTION IN...
 BIG DATA ANALYTICS FOR USER-ACTIVITY  ANALYSIS AND USER-ANOMALY DETECTION IN... BIG DATA ANALYTICS FOR USER-ACTIVITY  ANALYSIS AND USER-ANOMALY DETECTION IN...
BIG DATA ANALYTICS FOR USER-ACTIVITY ANALYSIS AND USER-ANOMALY DETECTION IN...Nexgen Technology
 
Internet Traffic Monitoring and Analysis
Internet Traffic Monitoring and AnalysisInternet Traffic Monitoring and Analysis
Internet Traffic Monitoring and AnalysisInformation Technology
 

Similaire à Social Network Analysis for Telecoms (20)

Meetup prague 201811_v01
Meetup prague 201811_v01Meetup prague 201811_v01
Meetup prague 201811_v01
 
AI Applications in telecommunication industry
AI Applications in telecommunication industryAI Applications in telecommunication industry
AI Applications in telecommunication industry
 
Proposal for System Analysis and Desing
Proposal for System Analysis and DesingProposal for System Analysis and Desing
Proposal for System Analysis and Desing
 
C05222124
C05222124C05222124
C05222124
 
Market basket predictive_model
Market basket predictive_modelMarket basket predictive_model
Market basket predictive_model
 
The data traffic and data warehouses store managing and controlling
The data traffic and data warehouses store managing and controllingThe data traffic and data warehouses store managing and controlling
The data traffic and data warehouses store managing and controlling
 
6620handout5o
6620handout5o6620handout5o
6620handout5o
 
Switching systems lecture3
Switching  systems lecture3Switching  systems lecture3
Switching systems lecture3
 
Massivegraph telecom ppt
Massivegraph telecom pptMassivegraph telecom ppt
Massivegraph telecom ppt
 
The Spring 2018 Undergraduate Symposium Poster
The Spring 2018 Undergraduate Symposium PosterThe Spring 2018 Undergraduate Symposium Poster
The Spring 2018 Undergraduate Symposium Poster
 
CyberDefPos_Scott
CyberDefPos_ScottCyberDefPos_Scott
CyberDefPos_Scott
 
IEEE 2015 C# Projects
IEEE 2015 C# ProjectsIEEE 2015 C# Projects
IEEE 2015 C# Projects
 
IRJET- Competitive Analysis of Attacks on Social Media
IRJET-  	 Competitive Analysis of Attacks on Social MediaIRJET-  	 Competitive Analysis of Attacks on Social Media
IRJET- Competitive Analysis of Attacks on Social Media
 
IEEE 2015 C# Projects
IEEE 2015 C# ProjectsIEEE 2015 C# Projects
IEEE 2015 C# Projects
 
Social Network Analysis
Social Network AnalysisSocial Network Analysis
Social Network Analysis
 
[Big] Data For Marketers: Targeting the Right Market
[Big] Data For Marketers: Targeting the Right Market[Big] Data For Marketers: Targeting the Right Market
[Big] Data For Marketers: Targeting the Right Market
 
Big Data and the Telecom Industry
Big Data and the Telecom IndustryBig Data and the Telecom Industry
Big Data and the Telecom Industry
 
Customer segmentation for a mobile telecommunications company based on servic...
Customer segmentation for a mobile telecommunications company based on servic...Customer segmentation for a mobile telecommunications company based on servic...
Customer segmentation for a mobile telecommunications company based on servic...
 
BIG DATA ANALYTICS FOR USER-ACTIVITY ANALYSIS AND USER-ANOMALY DETECTION IN...
 BIG DATA ANALYTICS FOR USER-ACTIVITY  ANALYSIS AND USER-ANOMALY DETECTION IN... BIG DATA ANALYTICS FOR USER-ACTIVITY  ANALYSIS AND USER-ANOMALY DETECTION IN...
BIG DATA ANALYTICS FOR USER-ACTIVITY ANALYSIS AND USER-ANOMALY DETECTION IN...
 
Internet Traffic Monitoring and Analysis
Internet Traffic Monitoring and AnalysisInternet Traffic Monitoring and Analysis
Internet Traffic Monitoring and Analysis
 

Dernier

Chandigarh Escorts Service 📞8868886958📞 Just📲 Call Nihal Chandigarh Call Girl...
Chandigarh Escorts Service 📞8868886958📞 Just📲 Call Nihal Chandigarh Call Girl...Chandigarh Escorts Service 📞8868886958📞 Just📲 Call Nihal Chandigarh Call Girl...
Chandigarh Escorts Service 📞8868886958📞 Just📲 Call Nihal Chandigarh Call Girl...Sheetaleventcompany
 
A DAY IN THE LIFE OF A SALESMAN / WOMAN
A DAY IN THE LIFE OF A  SALESMAN / WOMANA DAY IN THE LIFE OF A  SALESMAN / WOMAN
A DAY IN THE LIFE OF A SALESMAN / WOMANIlamathiKannappan
 
John Halpern sued for sexual assault.pdf
John Halpern sued for sexual assault.pdfJohn Halpern sued for sexual assault.pdf
John Halpern sued for sexual assault.pdfAmzadHosen3
 
Russian Call Girls In Gurgaon ❤️8448577510 ⊹Best Escorts Service In 24/7 Delh...
Russian Call Girls In Gurgaon ❤️8448577510 ⊹Best Escorts Service In 24/7 Delh...Russian Call Girls In Gurgaon ❤️8448577510 ⊹Best Escorts Service In 24/7 Delh...
Russian Call Girls In Gurgaon ❤️8448577510 ⊹Best Escorts Service In 24/7 Delh...lizamodels9
 
Enhancing and Restoring Safety & Quality Cultures - Dave Litwiller - May 2024...
Enhancing and Restoring Safety & Quality Cultures - Dave Litwiller - May 2024...Enhancing and Restoring Safety & Quality Cultures - Dave Litwiller - May 2024...
Enhancing and Restoring Safety & Quality Cultures - Dave Litwiller - May 2024...Dave Litwiller
 
Phases of negotiation .pptx
 Phases of negotiation .pptx Phases of negotiation .pptx
Phases of negotiation .pptxnandhinijagan9867
 
Ensure the security of your HCL environment by applying the Zero Trust princi...
Ensure the security of your HCL environment by applying the Zero Trust princi...Ensure the security of your HCL environment by applying the Zero Trust princi...
Ensure the security of your HCL environment by applying the Zero Trust princi...Roland Driesen
 
0183760ssssssssssssssssssssssssssss00101011 (27).pdf
0183760ssssssssssssssssssssssssssss00101011 (27).pdf0183760ssssssssssssssssssssssssssss00101011 (27).pdf
0183760ssssssssssssssssssssssssssss00101011 (27).pdfRenandantas16
 
Call Girls in Delhi, Escort Service Available 24x7 in Delhi 959961-/-3876
Call Girls in Delhi, Escort Service Available 24x7 in Delhi 959961-/-3876Call Girls in Delhi, Escort Service Available 24x7 in Delhi 959961-/-3876
Call Girls in Delhi, Escort Service Available 24x7 in Delhi 959961-/-3876dlhescort
 
Call Girls Pune Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Pune Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Pune Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Pune Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 
Katrina Personal Brand Project and portfolio 1
Katrina Personal Brand Project and portfolio 1Katrina Personal Brand Project and portfolio 1
Katrina Personal Brand Project and portfolio 1kcpayne
 
Call Girls From Pari Chowk Greater Noida ❤️8448577510 ⊹Best Escorts Service I...
Call Girls From Pari Chowk Greater Noida ❤️8448577510 ⊹Best Escorts Service I...Call Girls From Pari Chowk Greater Noida ❤️8448577510 ⊹Best Escorts Service I...
Call Girls From Pari Chowk Greater Noida ❤️8448577510 ⊹Best Escorts Service I...lizamodels9
 
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756dollysharma2066
 
Mysore Call Girls 8617370543 WhatsApp Number 24x7 Best Services
Mysore Call Girls 8617370543 WhatsApp Number 24x7 Best ServicesMysore Call Girls 8617370543 WhatsApp Number 24x7 Best Services
Mysore Call Girls 8617370543 WhatsApp Number 24x7 Best ServicesDipal Arora
 
Mondelez State of Snacking and Future Trends 2023
Mondelez State of Snacking and Future Trends 2023Mondelez State of Snacking and Future Trends 2023
Mondelez State of Snacking and Future Trends 2023Neil Kimberley
 
Call Girls Service In Old Town Dubai ((0551707352)) Old Town Dubai Call Girl ...
Call Girls Service In Old Town Dubai ((0551707352)) Old Town Dubai Call Girl ...Call Girls Service In Old Town Dubai ((0551707352)) Old Town Dubai Call Girl ...
Call Girls Service In Old Town Dubai ((0551707352)) Old Town Dubai Call Girl ...allensay1
 
Call Girls In Panjim North Goa 9971646499 Genuine Service
Call Girls In Panjim North Goa 9971646499 Genuine ServiceCall Girls In Panjim North Goa 9971646499 Genuine Service
Call Girls In Panjim North Goa 9971646499 Genuine Serviceritikaroy0888
 
Dr. Admir Softic_ presentation_Green Club_ENG.pdf
Dr. Admir Softic_ presentation_Green Club_ENG.pdfDr. Admir Softic_ presentation_Green Club_ENG.pdf
Dr. Admir Softic_ presentation_Green Club_ENG.pdfAdmir Softic
 

Dernier (20)

Chandigarh Escorts Service 📞8868886958📞 Just📲 Call Nihal Chandigarh Call Girl...
Chandigarh Escorts Service 📞8868886958📞 Just📲 Call Nihal Chandigarh Call Girl...Chandigarh Escorts Service 📞8868886958📞 Just📲 Call Nihal Chandigarh Call Girl...
Chandigarh Escorts Service 📞8868886958📞 Just📲 Call Nihal Chandigarh Call Girl...
 
A DAY IN THE LIFE OF A SALESMAN / WOMAN
A DAY IN THE LIFE OF A  SALESMAN / WOMANA DAY IN THE LIFE OF A  SALESMAN / WOMAN
A DAY IN THE LIFE OF A SALESMAN / WOMAN
 
John Halpern sued for sexual assault.pdf
John Halpern sued for sexual assault.pdfJohn Halpern sued for sexual assault.pdf
John Halpern sued for sexual assault.pdf
 
Russian Call Girls In Gurgaon ❤️8448577510 ⊹Best Escorts Service In 24/7 Delh...
Russian Call Girls In Gurgaon ❤️8448577510 ⊹Best Escorts Service In 24/7 Delh...Russian Call Girls In Gurgaon ❤️8448577510 ⊹Best Escorts Service In 24/7 Delh...
Russian Call Girls In Gurgaon ❤️8448577510 ⊹Best Escorts Service In 24/7 Delh...
 
unwanted pregnancy Kit [+918133066128] Abortion Pills IN Dubai UAE Abudhabi
unwanted pregnancy Kit [+918133066128] Abortion Pills IN Dubai UAE Abudhabiunwanted pregnancy Kit [+918133066128] Abortion Pills IN Dubai UAE Abudhabi
unwanted pregnancy Kit [+918133066128] Abortion Pills IN Dubai UAE Abudhabi
 
Forklift Operations: Safety through Cartoons
Forklift Operations: Safety through CartoonsForklift Operations: Safety through Cartoons
Forklift Operations: Safety through Cartoons
 
Enhancing and Restoring Safety & Quality Cultures - Dave Litwiller - May 2024...
Enhancing and Restoring Safety & Quality Cultures - Dave Litwiller - May 2024...Enhancing and Restoring Safety & Quality Cultures - Dave Litwiller - May 2024...
Enhancing and Restoring Safety & Quality Cultures - Dave Litwiller - May 2024...
 
Phases of negotiation .pptx
 Phases of negotiation .pptx Phases of negotiation .pptx
Phases of negotiation .pptx
 
Ensure the security of your HCL environment by applying the Zero Trust princi...
Ensure the security of your HCL environment by applying the Zero Trust princi...Ensure the security of your HCL environment by applying the Zero Trust princi...
Ensure the security of your HCL environment by applying the Zero Trust princi...
 
0183760ssssssssssssssssssssssssssss00101011 (27).pdf
0183760ssssssssssssssssssssssssssss00101011 (27).pdf0183760ssssssssssssssssssssssssssss00101011 (27).pdf
0183760ssssssssssssssssssssssssssss00101011 (27).pdf
 
Call Girls in Delhi, Escort Service Available 24x7 in Delhi 959961-/-3876
Call Girls in Delhi, Escort Service Available 24x7 in Delhi 959961-/-3876Call Girls in Delhi, Escort Service Available 24x7 in Delhi 959961-/-3876
Call Girls in Delhi, Escort Service Available 24x7 in Delhi 959961-/-3876
 
Call Girls Pune Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Pune Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Pune Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Pune Just Call 9907093804 Top Class Call Girl Service Available
 
Katrina Personal Brand Project and portfolio 1
Katrina Personal Brand Project and portfolio 1Katrina Personal Brand Project and portfolio 1
Katrina Personal Brand Project and portfolio 1
 
Call Girls From Pari Chowk Greater Noida ❤️8448577510 ⊹Best Escorts Service I...
Call Girls From Pari Chowk Greater Noida ❤️8448577510 ⊹Best Escorts Service I...Call Girls From Pari Chowk Greater Noida ❤️8448577510 ⊹Best Escorts Service I...
Call Girls From Pari Chowk Greater Noida ❤️8448577510 ⊹Best Escorts Service I...
 
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
 
Mysore Call Girls 8617370543 WhatsApp Number 24x7 Best Services
Mysore Call Girls 8617370543 WhatsApp Number 24x7 Best ServicesMysore Call Girls 8617370543 WhatsApp Number 24x7 Best Services
Mysore Call Girls 8617370543 WhatsApp Number 24x7 Best Services
 
Mondelez State of Snacking and Future Trends 2023
Mondelez State of Snacking and Future Trends 2023Mondelez State of Snacking and Future Trends 2023
Mondelez State of Snacking and Future Trends 2023
 
Call Girls Service In Old Town Dubai ((0551707352)) Old Town Dubai Call Girl ...
Call Girls Service In Old Town Dubai ((0551707352)) Old Town Dubai Call Girl ...Call Girls Service In Old Town Dubai ((0551707352)) Old Town Dubai Call Girl ...
Call Girls Service In Old Town Dubai ((0551707352)) Old Town Dubai Call Girl ...
 
Call Girls In Panjim North Goa 9971646499 Genuine Service
Call Girls In Panjim North Goa 9971646499 Genuine ServiceCall Girls In Panjim North Goa 9971646499 Genuine Service
Call Girls In Panjim North Goa 9971646499 Genuine Service
 
Dr. Admir Softic_ presentation_Green Club_ENG.pdf
Dr. Admir Softic_ presentation_Green Club_ENG.pdfDr. Admir Softic_ presentation_Green Club_ENG.pdf
Dr. Admir Softic_ presentation_Green Club_ENG.pdf
 

Social Network Analysis for Telecoms

  • 1. The Social Effect: Predicting Telecom Customer Churn with Call Data Michael E. Driscoll, Ph.D. Principal, Founder February 16, 2010
  • 2. Social Network Analysis with Telecom Data The following slides describe an initial project analyzing a N. American telecom’s call data on a dedicated analytics platform: We describe the analysis of a slice of a telecom’s call history data from several million customers in the several major North American markets. We demonstrate the performance gain achieved by having a dedicated analytics platform (computation of millions of relationships from tens of billions of events, spanning tens of TB of data, in less than one hour) We show that social network influence is a powerful predictor of customer churn: subscribers who experience a Telecom cancellation in their frequent calling network are 2x more likely to cancel themselves. We highlight one outbreak of cancellations in a metropolitan call network from May-June 2009.
  • 3. Challenge: Customer Churn Acquisition Attrition
  • 4. Key Data: Call Detail Records A slice of several billion call detail records (CDRs) from several million subscribers drawn from three major North American markets, for May-August 2009.
  • 5.
  • 6. What about social networks?
  • 7. Social Network Analysis Network is Generated from Call History Data Call history logs were pulled from the Greenplum warehouse. These were parsed and outgoing numbers were associated with subscription ids. The result is a row of data for every caller-callee connection meeting a low threshold (> 1 call and > 60 s talk-time per month). The majority are between Telecom customers and other carriers (or land-lines).
  • 8. Our Analytics Workflow Three steps: 1. Pull from DB, 2. Analyze in R, 3. Visualize in R + Graphviz
  • 9. Our Tool: The R Programming Language Download R at http://www.r-project.org/
  • 10. Getting Call Data Into R for Analysis - from Files > Calls <- read.csv(“CallHistory.csv”,header=TRUE) from Databases > con <- dbConnect(driver,user,password,host,dbname) > Calls <- dbSendQuery(con, “SELECT * FROM call_history”) from the Web > con <- url('http://Telco.com/dump/CallHistory.csv') > Calls <- read.csv(con, header=TRUE) from previous R objects > load(‘CallHistory.RData’)
  • 11. Social Network Analysis Millions of edges analyzed in minutes Full analysis of a first-order outgoing call network for our slice (~ millions of customers, three months of call history) took less than one hour. This could be further improved with further parallelization of R code (currently SQL queries run parallel on Greenplum, R is run on master node).
  • 12. Results: People Have Small Call Networks (Three) The median size of a caller’s network is three, while the mean size is five.
  • 13. Results: Canceling Customers are 7x More Likely to be Linked Types of Callers (Nodes) active (A) cancelled (C) Types of Connections (Edges) A-A A-C or C-A C-C C-C edges are 7x more likely in call networks than what is expected by chance
  • 14. Results: A Customer With a Canceller in Their Network Churns at Twice the Rate Types of Connections (Edges) May C-A June C-C In essence, we are asking whether being connected to another canceller has any effect on one’s rate of cancellation. It turns out that it does. And if we only look at voluntary port-outs, we see that customers churn at 3x the rate.
  • 15. From Data to Insights to Actions If we had known two customers’ calling networks… Could we have prevented four more from leaving?
  • 16. The Emerging Analytics Stack Actions Apps (Email, Ad Campaigns) Analytics (R, SPSS, SAS, SAP) Insights Big Data (HDFS or Parallel RDBMS) Data
  • 17. References Enhancing Customer Knowledge at Optus, Teradata Case-Study (September 2009). IBM’s Analytics Tapped to Predict, Prevent Churn. Telephony Online (April 2009). The Elements of Statistical Learning, Hastie, Tibshirani, Friedman. Springer. (February 2009). Study Shows Obesity Can Be Contagious, Gina Kolata, The New York Times (July 25, 2007) [great example of homophily] Contact Michael E. Driscoll, Ph.D. med@dataspora.com Follow @datasporaon Twitter

Notes de l'éditeur

  1. Most telcos lose 1-2% of their customers every month.It’s 7x more expensive to acquire a customer, than to retain.
  2. Birds of a feather flock together; cancellers clump together, so do active users. Like vinegar and water, we see enrichment for “like-like” edges in our network, and dilution of “dissimilar” edges (the A-C or C-A). Upshot: people cancellationQuestion: is this all an artifact of family plans – where a bunch of subscribers quits together? In part yes, but the trends hold up even when we do a temporal analysis.
  3. Key take-home point here is that this analysis , looking at the May to June transition, removes
  4. The stack is loosely coupled: right tool for the right job. The need for a dedicated analytics RDBMS