Telecom operators worldwide, including wire-line, wireless, Internet and cable operators, have spent billions of dollars on business intelligence (BI) software, services and systems integration over the past few years. These investments have encompassed a wide range of business processes within an operator’s organization, such as network planning/operations, service assurance, marketing, product management, revenue assurance, fraud/risk management and customer management. These approaches have proven useful, but are essentially retrospective.
Today, telecom operators are continuously challenged by:
- New telecom entrants (greenfield operators, MVNOs).
- The introduction of creative and innovative offerings from existing and new competitive operators.
- Ensuring quality of service (QoS) to existing subscribers to enhance customer satisfaction.
- Efficient and effective revenue leakage management – managing accurate call details, tracking inter-carrier exchange points, etc.
- Cost-effective network growth planning to optimally manage capex without compromising QoS.
Fierce competition has forced operators to reduce their tariffs drastically, resulting in decreased average revenue per user (ARPU). Further, late entrants and greenfield operators, being less burdened by legacy and backward-compatibility issues, are able to offer very attractive value-added services to lure customers from incumbent operators. The churn in the subscriber base is further exacerbated by the regulatory mandate of mobile number portability, providing a very weak barrier against subscribers switching operators. Operators must ensure that subscribers get the requisite quality of service to maintain brand loyalty.
Significant increases in traffic volumes strain the older systems which have difficulty in capturing all of the relevant data needed to monetize network usage—resulting in revenue leakages at various network points—especially at the inter-carrier exchange points. A recent study by Frost & Sullivan’s analyst and consulting group Stratecast, estimates that plugging inter-carrier leakage can result in approximately 3%-5% savings for an operator—equating to several millions of dollars annually.
Ensuring QoS for existing subscribers requires proactive monitoring of critical network health parameters and planning for capacity upgrades before congestion occurs in the network. Typically, for want of sophisticated tools, operators end up over-provisioning the network, thereby leading to additional capital expenses with a long cycle before getting adequate returns for this investment. With a decline in ARPU, all such “wasted” expenditures impact the profitability of the operator.
Telecom operators are favorably positioned because of their access to large amounts of data. There are primarily two sources of this data.
1. Network data—pertaining to link status/availability, utilization, network latency, call set-up time, inter-exchange of data at operator peering points etc.
2. Subscriber data—related to call and service usage, location (varying degrees of accuracy).
This voluminous data is a starting point for the operator. Using a combination of real-time and non-real-time data extraction, cleansing, analytics, mining, warehousing and reporting techniques on this data, the operator can develop innovative solutions to address some of the challenges highlighted in the earlier section.
Technology Solutions—Scope for Innovation
Some of the innovative applications that can be developed using BI/analytics techniques on the data available with the operators are included here.
Network Data Analysis
Proactive Network Monitoring
Network monitoring tools generate huge amounts of data pertaining to the health of the network. Leveraging such historical information and building online analytical processing (OLAP) cubes can help the operator make meaningful use of the data. Further, using sophisticated correlation techniques helps the operator to do root-cause analysis of network outages and proactively subvert future outages.
Proactive network monitoring helps the operator to maintain a healthy network, consequently resulting in increased customer satisfaction and better retention in light of strong competition.
Capital expenses contribute significantly to the overall cost of running a network. Operators invest in network capacity to address scalability and future growth. Since this growth can be unpredictable, operators typically over-provision their networks—leading to significant amounts of unutilized capacity that cannot be immediately monetized.
Data mining and correlation techniques applied successfully on network data help the operator identify heavily utilized parts of the network at different points in time. This helps the operator to make key decisions related to adding capacity at the right location at the appropriate time. This analytics-assisted capacity planning, combined effectively with dynamic traffic routing, helps operators to optimize network resources—leading to overall cost reductions.
Minimizing revenue leakages helps operators monetize services that have already been provided to subscribers. Revenues are computed for usage of services on the basis of call detail records (CDRs) that are generated from various network locations. CDR volumes for some large operators can be as high as 5-8 terabytes per day, a figure that continues to grow year-over-year with increasing network utilization. Managing and storing such huge volumes of CDRs is a very complex undertaking. Further, multiple CDRs are generated for the same service and some of these CDRs are incomplete. This leads to the operator’s inability to accurately monetize services based on these CDRs.
Speedy correlation of multiple CDRs and enrichment of these CDRs is the first step toward reducing the complexity of CDR management. Further, OLAP cubes built on these CDRs help in maintaining aggregated data with the required level of flexibility. The data can be analyzed from different perspectives with varying levels of detail through slicing, dicing and drill down/up. Such techniques help the operator maintain an accurate tracking of service usage. This accuracy is crucial in minimizing revenue leakages, especially at inter-carrier exchange points (peering points).
General Analytics Solution for a Telecom Company
Subscriber Data Analysis
Operators have access to large amounts of data about a subscriber, based on their usage of the operators’ services. Analysis of calling patterns, billing data and support requests, when combined with subscriber’s personal information such as demographics, age, gender, home address and income, forms the basis for creating a profile of the subscriber. For mobile and wireless services, current location and changes to the location provide additional context for the subscriber’s profile.
The subscriber profile becomes the basis for other innovative services.
Social Network Modeling and Analysis
By leveraging calling patterns and other data points from a subscriber’s profile, operators can build a social networking model for the subscriber that identifies connections and proximities between different subscribers. The social network model deduces these proximities through data analytical techniques and is periodically validated and reinforced through automated and manual actions.
Given the lower ARPU and competitive environment, operators are exploring alternate sources of revenue. Advertisement-based revenue is one such popular source. Randomized advertisements, being intrusive and interruptive, can adversely affect the subscriber’s satisfaction with the operator. On the other hand, personalized advertising that caters to the likes and needs of the individual can enhance loyalty. These advertisements, when combined with context-specific information such as location, can significantly improve the “hit-rate.” Further, advertisers are amenable to paying premium rates for personalized advertising to the targeted audience, resulting in increased revenues for the operator.
Up-Selling and Innovative Tariffs
The 80-20 principle holds true for most operators—wherein 80% of the revenue comes from 20% of the high net-worth subscribers. The analysis of service usage and billing can help the operator identify the top 20% of subscribers and focus their attention on improving loyalty by ensuring high subscriber satisfaction. Specifically, tariffs can be personalized to provide the best value for the subscribers’ money without reducing operators’ ARPU—a win-win situation. Further, this analysis also provides an opportunity to up-sell additional services (preferably personalized) based on subscribers’ profiles.
Competition among operators (especially mobile operators) lends itself to increased subscriber churn because subscribers have multiple options to select from. This is further exacerbated by mobile number portability, reducing the barrier for churn. To retain their subscriber base, it is important for operators to proactively identify subscribers who are likely to churn and incentivize them to stay. Many techniques, including social network modeling, can be used to identify the subscribers who are most likely to switch out. The churn management solution is integrated with the CRM systems to ensure that appropriate actions such as personalization of tariff, discounts etc. are offered to retain the customers.
BI in Practice
Leading companies with BI/analytics technology expertise are delivering customized BI solutions for the telecom industry. For example, Persistent Systems has developed an innovative mobile-based advertising service for one of its customers that leverages the caller ring back tone as the channel for delivering personalized advertisements. The combination of several BI / analytics techniques—including subscriber profiling, demographics, social network analysis—with manual feedback and automated learning help to accurately select the advertisement appropriate for a specific user. This highly scalable (greater than 300 calls per second), robust (24/7), distributed, low latency (less than 50ms) product has been successfully deployed in a tier-1 carrier in India supporting more than 100 million subscribers.