Telecom IQ
Showing results for 
Search instead for 
Did you mean: 

Complex Event Processing (CEP): A key for real-time, context aware, analytics


Unlike many other industries, the promise of Big Data for Communication Service Providers (CSPs) depends on contextualization. To achieve an expected business impact or outcome, CSPs must be able to process data streams in real-time and act on them within proper context.

Complex Event Processing is a key element in this process, helping CSPs collect and correlate current data into actionable events.


Why real-time analysis is crucial

Information is emerging as the new currency of business, and remains the basis for true competitive differentiation, innovation, value creation, growth, and risk mitigation. But simply having access to information before industry competition is not enough today – CSPs also need to act within the context of the customer experience. Data processing and analytics must occur in real-time and be complemented by real-time action-ability.


Complex Event Processing defined

A Complex Event Processor (CEP) is an analytical function designed for CSPs to perform real-time monitoring of contiguous flows of events, reports, and measurements collected from a variety of sources.  

To do that, a CEP must have the ability to perform continuous queries and analyses on data streams, and also maintain event histories for performing correlated trend analytics and pattern detection over longer periods of time. Naturally, a CEP must be designed for massive scalability in order to cope with CSPs’ high-volume, highly distributed data sources.


What are the must haves?

Functional requirements for a CEP include:

  • Ability to capture data generated in and out of an operator’s network across multiple sources and applications
  • Identification of complex events/patterns by correlating multiple sources of streaming and non-streaming data, including historical data
  • Real-time online calculations (i.e. statistical functions over a few seconds of sliding windows of incoming data)
  • Notification of external applications when specific complex events or conditions are met

A modular implementation of a CEP is likely to include the following building blocks:

  • Loaders: capturing data from incoming sources when streaming social networks, high throughput deep packet inspections boxes or static databases
  • Event Processing Agents: performing pattern detection, conditioning, filtering, and correlation of data from multiple sources
  • Writers/Notifiers: informing client applications and updating business processes in real-time


Business examples

Complex event processing serves CSPs in many of their Big Data business processes, including:

  • Customer Experience Management: analyzing consumption of CSP services to detect abnormal situations impacting the perceived Quality of Experience. CEP helps to calculate network and users KPIs at the time they are connected, and react in real-time. This is key to maintaining end user satisfaction.
  • Identify Frauds: taking inputs from a wide range of sources, including SIM/IMSI data, activations, history of fraudulent customers, and bad debt data. With all this data being correlated while the customer is in communication with customer care, CEP helps to identify subscription frauds in real-time and deny the service before subscription. This saves substantial amounts of money.
  • Location Aware Marketing: collecting and analyzing data in real-time from various customer information sources, including voice and data networks and application portals. Data is statistically analyzed to produce in-depth subscriber insights—including preferences, interests, web browsing behavior, and location presence patterns. Combined with historical data, analysis provides satisfaction index, propensity scores, and other insights. Services and ads can then be effectively delivered and personalized, enhancing the overall customer experience.

You can read more about CEP at our Telco Big Data page:

0 Kudos
About the Author


Oded manages Go-To-Market enablement and Solution Marketing for HPE’s Communication Services Business (CSB), His focus is solutions of Subscriber Awareness that allow CSPs to evolve to Customer Centric service delivery, Oded is responsible for bringing together Products, Business, Operations, Sales and Marketing into a coherent Go-To-Market Strategy, across all regions, counties and market segments.

Jan 30-31, 2018
Expert Days - 2018
Visit this forum and get the schedules for online HPE Expert Days where you can talk to HPE product experts, R&D and support team members and get answ...
Read more
See posts for dates
HPE Webinars - 2018
Find out about this year's live broadcasts and on-demand webinars.
Read more
View all