Customer Usage Pattern Analysis for a fixed line/ cellular customer

In the competitive telecom industry where the billing of a customer has gone to the level of 1/2 paise per minute the most important part is the selling of right plans and right packages to the customers. The APRU (Average revenue per user) can be increased only with the knowledge and in depth understanding of the user pattern. An added advantage that works for the telecom industry is that every time a call is placed on the network, detailed and descriptive information about the call is saved as a call detail record. Thus the need for a micro market research is not needed for the understanding of the customer usage pattern. The call detail records act as the primary source of data mining. Considering that even if call detail records that are generated and stored to a last timeline of 12 months it means millions of call detail data will need to be stored at any time. Call detail records include sufficient information to describe the important characteristics of each call.

At a minimum, each call detail record will include

• The originating and terminating phone numbers
• The network to which the call is dialed
• Date and the time of the call
• Duration of the call.

With the advent of real time recording for prepaid the day the calls were made, and the details of the call will be available almost immediately. For post paid customers though the data registry might take some time till the batch run for the end of day for data mining.

The unbilled amount though is readily available on the IVR and the customer self help- websites, the billing data is typically made available only once per month in total. Call detail records can not be used directly for conclusive results by data mining, since the goal of data applications is to extract knowledge for a customer level but the variation in the usage pattern can predict the volume and trends at phone call level. With telecom companies giving a discount which varies as per time and location of the call made this will add to another few columns in the data mining to determine the profitability of the customers and discount schemes and also help in creating new products and service opportunities. Thus call detail records for a customer can be summarized into a single record that can depict the customer’s calling behavior.

To understand the usage pattern the customer segmentation and customer profiling must be done correctly.

Customer Segmentation

Segmentation is a way to have more targeted communication with the customers. The process of segmentation describes the characteristics of the customer groups (called segments or clusters) within the data. Segmenting means classifying the population in to segments according to their affinity or similar characteristics. Customer segmentation is a preparation step for classifying each customer according to the customer groups that have been defined. Customer segmentation and customer profiling are of prime importance in order to do a usage pattern analysis

Customer Profiling

Customer profiling provides a basis for marketers to ’communicate’ with existing customers in order to offer them better services and retaining them. This is done by assembling collected information on the customer such as demographic and personal data. Customer profiling is also used to prospect new customers using external sources, such as demographic data purchased from various sources. This data is used to find a relation with the customer segmentation that were constructed before. This makes it possible to estimate for each profile (the combination of demographic and personal information) the related segment and visa versa. More directly, for each profile, an estimation of the usage behavior can be obtained.

Parameters for Customer Profiling

• Geographic Location
• Cultural and ethnic
• Company size
• Economic conditions (Spend Analysis)
• Age and gender
• Values, attitudes and beliefs (Customer Loyalty)
• Life cycle (Period of association)
• Knowledge and awareness of other products (Inquiries, Oppty, Surveys etc)
• Lifestyle (Products and services apart from the current product)
• Acquisition Method (How was the customer acquired)
• Credit and payment history (Historical data and credit rating)

After the segmentation and profiling  of a customer has been done the usage pattern analysis of a customer can be proceeded to have a focused approach

Primary Parameters for Customer Usage Pattern Analysis

• How (Prepaid, Postpaid)
• Who (Calls to Fixed line, Cellular phones etc)
• What (Location of customer call origination and recipient call)
• Which Area (Area and Tower wise analysis)
• When (Day/ Time of the call)
• Where (Local, Intra state, Inter state, International)
• How long (Duration of the call)
• How often (How often does the customer make/ receive call)
• Who is the service provider (Same service provider/ different provider)

Secondary/ Drill Down Parameters for Customer Usage Pattern Analysis

• Average call duration
• Average no of calls received per day
• Average no of calls originated per day
• Daytime calls (9am - 6pm)
• No of weekday calls (Monday - Friday)
• No of calls to mobile phones
• No of calls to landline
• No of inter state calls per day
• No of international calls
• No of outgoing calls within the same operator
• No of outgoing calls to other operators
• Usage of Data services (text messages, internet over phone, mcommerce)
• Usage of Value added services (caller tunes, ringtones, reality show polls, video clips, social networking sites, mobile apps, info services, wallpapers, mobile tv etc )

Thus a dashboard can be created for the sales analysis team which has
Histograms for

• Visualization of phone calls per hour ( X Axis:- Hours, Y Axis:- Calls No )
• Region wise Call histograms with Y Axis:- Percentage of customers and

                      X Axis:- Average Call duration
                      X Axis:- Average No of calls per day
                      X Axis:- Percentage of Day time calls
                      X Axis:- Percentage of Weekday calls
                      X Axis:- Average number of calls outgoing per day
                      X Axis:- Billing Range of the customers
                      X Axis:- Number of sms send by the customer

Also due to the advent of Smartphones, 3G and VAS there needs to be a dashboard for the product development which can depict

• Pie chart for Product wise volume of usage
• Pie chart for product wise share of billing to the customer
• Mixed bar graphs for depicting the billing per customer in the same segmentation and profile
• Comparative graphs for comparing the ARPU per user across segments thus providing a campaign decision support

Thus mapping the consumer behavior and defining the usage pattern is the key to  Redefine the Strategy to position products, services in the market and gain a competitive edge in sales using the sales analytics vs. the competitors.

*** Due to confidential of data graphs, detailed report not available