Monetizing Big Data with Streaming Analytics for Telecoms Service Providers

3,541 views
3,343 views

Published on

The SQLstream Blaze (http://www.sqlstream.com) real-time data hub enables telecommunication service providers to leverage their streaming Big Data, and to integrate and analyze streams of CDR, device, network and service data in real-time. Streaming analytics and automated actions can be used to optimize service and network performance in real-time, optimize Customer Care workflows for efficient troubleshooting and reduced costs,and real-time fraud detection and prevention from CDR analytics. The result is improved operational efficiency, better delivered services and an customer satisfaction.

Published in: Technology

Monetizing Big Data with Streaming Analytics for Telecoms Service Providers

  1. 1. MONETIZING BIG DATA with STREAMING ANALYTICS! For Communications Service Providers and the Telecoms Industry Copyright © 2014 – Proprietary and Confiden7al Informa7on of SQLstream Inc.
  2. 2. SCOPE § Explain real-time Big Data and streaming analytics § Explore real-time applications in the Telecoms industry § Share our thoughts, experience and use cases 2Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc.
  3. 3. Today’s Presenter Ronnie Beggs Vice President Marke3ng & Product Management, SQLstream § Over twenty years experience of product management, marke7ng and business development in the real-­‐7me soKware business. § Worked for a number of successful start-­‐ups, from early stage through to acquisi7on, including Metrica (ADC) and Cramer Systems (Amdocs). 3Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc.
  4. 4. About SQLstream Distributed stream processing plaYorm for opera7onal intelligence and the Internet of Things, delivering streaming analy7cs and real-­‐7me ac7ons facts § Launched 2009 from log and sensor machine data. § Worldwide customer base across mul7ple industries § Strategic partnerships for opera7onal intelligence (logs) and Internet of Things (sensors) capabili7es § Process unstructured and structured machine data § Accelerate and extend Hadoop & RDBMS § Open, standards-­‐based plaYorm based on SQL 4Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc. differen7ators § Massively scalable streaming data plaYorm § Only true standard SQL streaming engine § Covered by 7 broad patents for stream processing
  5. 5. What’s happening with Big Data? § Stored information doubling every 18-24 months § “Internet of Things” is creating new data with no human interaction § Business decisions need to happen faster based on real-time, actionable intelligence § Streaming and predictive analytics are changing the way we interact with our operational systems and customers. 5Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc.
  6. 6. Looking Forward with Streaming Analytics § Enterprises have been managed based on prior history delivered at the end of the day, month or quarter. § Streaming analytics enables enterprises to drive their business in real-time, reacting to changes and opportunities as they happen. 6Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc.
  7. 7. Telecoms and Big Data $5.4B Communica7ons analy7cs market by 2019. Market Research Report.biz AREAS OF NEEDS § Customer Experience § Fraud prevention § IP Network & Service Performance § Call Center Experience 7Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc. Streaming Value Improved opera7onal efficiency and customer sa7sfac7on, with a real-­‐7me 360o customer view, and con7nuous data silo integra7on Call Centers| Telecommunica7ons | Data Centers ISSUES § Untapped New (Big) Data § Ease of churn § Lacking a 360o customer view
  8. 8. Streaming Analytics as a Complement to Traditional Data Management Repeated Queries DATABASE Collect, translate, classify DATA 8Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc. ANALYSIS PATTERN DETECTION ACTION TIME STREAMING DATA ANALYTICS PLATFORM DATA Ac7on Ac7on C-­‐ETL Aggrega7on Classifica7on Profiling Deep analy7cs Trend detec7on Trend correla7on Extrapola7on Alerts Ac7ons Seconds Hours -­‐> Days DATA DATA
  9. 9. OPERATIONAL INTELLIGENCE Integrating Operations and Analytics in Real-time Real-time Operational Intelligence Business Intelligence As we move toward a real-time business environment, the capability to process data flows swiftly and flexibly will become increasingly important. SQLstream leads the industry in this kind of capability. ” Robin Bloor 9Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc. Chief Analyst for Bloor Group Operations Continuous monitoring and analytics Improve decision-making Automate operational processes Billing Rating QoE Network analysis Fraud Monitoring ”
  10. 10. The Information Value Chain What is happening? 10Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc. What might happen? What just happened? Make stuff happen!
  11. 11. Telco Big Data! An Overview
  12. 12. Actionable insights - the ideal scenario SOURCESSYSTEMS & APPS 12Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc. Alerts ENTERPRISE § Operations § Customer Care § Marketing § Logistics MACHINE DATA § Unstructured § Semi-structured § Structured § Log, sensor & network QoE STREAMING ANALYTICS Actions Dashboards Continuous ETL
  13. 13. What’s possible from xDRs | APPLICATIONS NETWORK SERVICE CUSTOMER BUSINESS § Op7miza7on of network u7liza7on § Network Capacity planning § Anomaly detec7on & troubleshoo7ng § Monitoring and protec7on § Self-­‐healing networks § Partner rou7ng § Subscriber profiling and informa7on § New product rollout visibility § Product development and tariff op7miza7on § Yield management and dynamic pricing § Service personaliza7on 13Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc. § Customer loyalty management § Churn preven7on § Device analysis § Campaign management and precision marke7ng § Contact center alerts § New customer experience monitoring § Billing accuracy and revenue § SLA management § Interconnect billing analysis § Real-­‐7me reports § Fraud and suspicious traffic detec7on
  14. 14. TECHNICAL CHALLENGES
  15. 15. Data Analysis Today – far from Real Time Current architectures § Multi-stage process § Offline ETL § Interim storage with no analytics capability ETL / RDBMS process challenges § Volume and Velocity § Variable, changing formats § New types and formats IMPACT § High Cost of Ownership § Delays to process the billing information § Delays in external distribution to partners 15Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc. BI Queries and Aggrega4on Scripts WAREHOUSES Near-­‐term data storage PLATFORMS Real-­‐4me ETL
  16. 16. STREAMING ANALYTICS ARCHITECTURES
  17. 17. Generating Operational Intelligence | Process Internet of Things & Sensors § Smart City § Transporta7on § Industrial Internet § Telema7cs § Smart Energy Opera3onal Intelligence & Logs § Security Intelligence § Servers & Applica7ons § Networks & Services Streaming Enterprise Hadoop and Data Warehouse integra7on for joining streaming and stored trend data Machine Data Social Media & TwiDer 17Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc. Real-­‐3me Ac3ons Real-­‐3me Dashboards Con3nuous Data Warehouse Updates Automated Ac3ons Con7nuous SQL queries over live data streams genera7ng streaming analy7cs and driving real-­‐7me ac7ons
  18. 18. CDR and IPDR Analysis! Where is the intelligence? Timestamp Transaction TRANS,2013-02-17-15:30:22,3458783,2347897953,128.56.0.253,STATUS:-15, DE69975, 4157588342 Log Details Web Server Logs CDRs Device Locations Twitter Timestamp [Sun Feb 17 15:30:49 2013] [notice] srv-sfo-08 caught SIGTERM, shutting down [Sun Feb 17 15:30:49 2013] [notice] Apache/2.2.21 -- resuming normal operations TERMINATE,ctl09gsx,01299796304,GMT-08:00,02-17-13,15:21:00,9,387,64ms,02-17-13,15:30:55,0005, IP-TO-IP,4157588342,8775715775,1,0,4157588342,RD_AXY_NN0_001,SFR01AAG34,40.50.245.60, 234.234.60.75,65678,411,399,SIP,SANFRANCISCO,0x4B1698,0x0005E,0x49768,4157588342,0198873465 <id>1597831220</id><deviceid>0198873465</deviceid><lat>lat=47.643957</lat><lon>lon= -122.3269</lon><time>2013-02-17T15:37:26Z</time><bearing>223.4535</bearing> <id>1597865781</id><deviceid>0198873465</deviceid><lat>lat=47.645982</ lat><lon>lon=-122.327500</lon><time>2013-02-17T15:37:26Z</time><bearing>200.6138</bearing> <id>1597940125</id><deviceid>0198873465</deviceid><lat>lat=47.647381</ lat><lon>lon=-122.326501</lon><time>2013-02-17T15:37:26Z</time><bearing>87.4357</bearing> {"created_at:Thu Feb 17 15:30:55 +0000 2013,id:304612775055998976,id_str: 304612775055998976,text:@MyServiceProvider today sucks, keeps dropped!,source:u006ca href=http:www.url.com rel=nofollow,followers_count:147,friends_count:10142, location: San Francisco, time_zone: Pacific, geo_enabled:true, location:u00dcT: -6.1987552,106.8661953, screen_name:APerson 18Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc. Timestamp Timestamp Timestamp Customer Mobile # Mobile # Term Reason Device ID Device ID Loca7on Loca7on Service Provider Fail Code Server
  19. 19. Enterprise-Class Real-time Data Hub Stream Processing for Operational Intelligence and the Internet of Things SQLstream Blaze 19Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc. s-Visualizer real-time dashboards for Enterprise Power Users s-Server StreamLab Intelligent guided data stream discovery, analytics and visualization without coding Distributed SQL Stream Processor s-Dashboard HTML5 real-time dashboards for Developers Storm Adapter s-Studio Developer & Admin
  20. 20. SQLstream Blaze – Core Platform Architecture Interac3ve Stream Discovery and Visualiza3on Web Sockets Stream Processing Engine Machine Data Agents Enterprise Systems Data Warehouse SQL Database Predictive Analytics 20Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc. Repor3ng Tools JDBC Control Systems SQL Optimizer Parallel Scheduler Real-time Indexing RT Memory Manager Dynamic Java Analytics (UDX) Streaming Data Protocol (HTML5)! Discovery API Connect Remote Systems Agents Enterprise Systems Devices & Apps Native Tables Web Agent REST (HTML5)! Dashboards (Flash)! Dashboards JDBC Adapters Devices & Apps JDBC Adapters Hadoop / HDFS HBase Storm & Kafka Enterprise BI Hadoop & NoSQL
  21. 21. StreamLab! Intelligent guided data stream discovery and visualization in minutes 1. Connect to the data sources 3. Streaming dashboards 21Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc. 2. Structure, filter and format the streams Interactive Stream Browser Suggestions Tool User History
  22. 22. Case Studies
  23. 23. Case study: Real-time Call Fraud Prevention Customer call profile 23Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc. Alerts Triggers Reports STREAMING ANALYTICS • Call suspension • Acct. suspension Destination• Email Alerts Location IP spoofing alerts duration Mo Tue Wed Thu Fri Sat Sun ① LA ② Nairobi ③ NY ④ ….. ① LA ② SF ③ NY ④ …. ① LA ② Detroit ① LA ② LA1 Dashboards
  24. 24. Real-time Call Rating & Fraud 24Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc. “SQLstream allows Veracity to provide vital real-­‐7me reports to our customers that previously took hours to create. SQLstream also provides real-­‐7me monitoring and insight into network concerns allowing Veracity to proac7vely address any such issues” Veracity Networks § Internet provider § Residen7al and business § Range of IP-­‐based services OPPORTUNITIES § CDR/IPDR real-­‐7me analy7cs § Real-­‐7me ra7ng and QoE § Fraud preven7on BENEFITS § Improved customer sa7sfac7on § Improved bandwidth u7liza7on § Improved fraud detec7on 7mes
  25. 25. Customer Benchmarked Performance! Large Network & Telecom Equipment Manufacturer 25Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc. SQLstream Network Data Network Data Network Data Network Data Network Data ENRICH ANALYZE SHARE Remote Agent Remote Agent Remote Agent Remote Agent Remote Agent Data Warehouse External Systems External Data PERFORMANCE STATISTICS System Throughput: 1.35M events / sec Server Configuration: 1 x 4-core CPU Event Size: ~1KB Data Sources: Many SYSTEM CHARACTERISTICS Collection: Intelligent Remote Agents (Distributed) Enrichment: Streaming data augmentation Analytics: Temporal & spatial pattern detection Output: Data warehouse + applications (JDBC)
  26. 26. Conclusions § Drivers for Streaming Data Analytics § Declining revenue streams § Increasing data monetization gap § A Big Data problem: Volume, Velocity and Variety § Current technology and solutions are far from real-time § SQLstream’s Real-time Advantage § Low latency correlation, alerts and actions across all data sources § Streaming enrichment § Continuous integration with existing platforms § Drives real-time rating, billing, QoE and QoS, and fraud 26Copyright © 2014 – Proprietary and Confidential Information of SQLstream Inc.
  27. 27. Download SQLstream Blaze for free!! www.sqlstream.com/downloads Contact us: Email: inquiries@sqlstream.com Call: +1 877-571-5775 Ronnie Beggs | ronnie.beggs@sqlstream.com | +1 415 758 8342 | @sqlstream Copyright © 2014 – Proprietary and Confiden7al Informa7on of SQLstream Inc. Twitter: @sqlstream Facebook: facebook.com/user/sqlstream LinkedIn: linkedin.com/company/sqlstream

×