Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Active insight behavioral targeting in the cloud


Published on

  • Be the first to comment

  • Be the first to like this

Active insight behavioral targeting in the cloud

  1. 1. Event Stream Processing in the Cloud ACTIVE INSIGHT Mike Telem Business Development
  2. 2. Table of Contents > Background: The Digital Era > Processing, Correlating and Aggregating Events > Use Cases: From Behavioral Targeting to Electrical Smart Grids > ESP in the Cloud > Roadmap: Where is ActiveInsight headed
  3. 3.  Our world is becoming digital…  Cell phones, web sites, GPS devices, cars, ads, Financial transactions,…  RFID, industrial eq., security sensors, border controls, medical eq.,…  Utilities, pipelines, meters, digital signage, home appliances, entertainment devices, cars, …  Applications, infrastructure, web- services, customer data,…  Markets, stocks, currencies, news, wiki’s, blogs, tweets,…  …  Multiple events share various perspectives  Event stream quantity and frequency will fluctuate  Effective time window for reactions is minimal  Reaction channels may vary  Events should be correlated with historical data The Digital Era
  4. 4. Building blocks of Behavioral Targeting  Event Stream Processing:  Processing application level events in a distributed environment  Event Correlation – Directing multiple event streams based on their context to the corresponding ESP containers  Complex Event Processing:  Processing multiple events to detect meaningful patterns using correlation, aggregation and time- frames  Pattern detection: Detecting specific event combinations and patterns in contexts  Cross-Context Correlation: Processing multiple streams into multiple contexts / perspectives (fraud / marketing)  Aggregation: Accumulating correlated events into time-based contexts, support for “event state machine” aggregation.  Data Integration: Caching data sources as “reference data” for processing  Reaction: Invoking an action after a successful event or pattern match
  5. 5. Different Use-cases > Similar Challenges  Online Gaming : Real-time BI, money laundering, local compliance, application offload  Online Advertisement: Behavioral targeting, multiple site click-stream correlation  Ecommerce : Identifying customer interests (up-sell/cross—sell) , Improving conversion rates, anonymous user hooking, campaign management  Online Self-Service : Identifying customer turnover or dissatisfaction, Monitor user experience and assist in transaction completion  Algo-Trading : performance and availability improvements and HW cost reduction  Auditing: Feeding “Who” did “What” and “When” to auditing and SIEM systems  Fraud detection: Fraudulent behavior pattern detection, Bot detection, alongside fraud detection systems  Electrical smart-grid: Detecting misuse, mal-functions, on-demand supply  Home Land Security: Enhance airport and border security, correlate multiple events, intelligence data and incoming alerts  Traffic management: Vehicle location management for Insurers, authorities and drivers  …Similar Challenges
  6. 6. React Different Use-cases > Similar Challenges Match Correlate Process Aggregate
  7. 7. Behavioral Targeting in the Cloud  Elastic  On-demand usage  Scaling up and out to varying event frequencies  … as a service  Offloading event processing  Dynamic Stream Sources  Dynamic event sources  Handling remote event sources  SaaS Enabler  Porting event-oriented applications to the cloud  SaaS component  Enhance SaaS applications  Offload the core application  Comply to regional regulations  Provide SaaS Application integration  IaaS/Hosting  Value Added Services (Security, Auditing, BI)  Customer Experience Management
  8. 8. ActiveInsight Distributed Behavioral Targeting Platform  Real-time event processing  Multi-source event stream processing  Event correlation and aggregation  Pattern matching  Integrated data caching  Embeddable framework  Scalable, elastic cloud run-time
  9. 9. Process Correlate Aggregate Match React Sample Architecture AI Server Node Distributed Cache Reference Data Context Process Match React Context AI Server Node Distributed Cache Reference Data Context Process Match React Context AI Server Node Distributed Cache Reference Data Context Process Match React Context Contexts Marketing Security Web App Mobile Device Car GPS
  10. 10. Unique Value Proposition  Embeddable, Real-time data stream processing  Flexible and dynamic pattern definition/detection  SpringSource development platform interoperability  Real-time, pattern-based logic invocation  Business driven behavior detection  User-centric actionable events  Real-time, value-based event feeds & user interactions  Non-intrusive deployment  Support for extreme transaction rates “With ActiveInsight organizations can identify up-sell and cross-sell opportunities, react to potential customer churn in time to prevent it, improve online self-service to customers and detect potential fraudulent activity in real-time “
  11. 11. Q&A Thank you!
  12. 12.