The Indian mobile telephony market is a classic example of a volume based strategy. Average revenue per user (ARPU) is one of the lowest, while the subscriber figures are second only to China. The market itself is highly fragmented with more than 5 players holding less than 90% of the market. In this scenario, identifying new sources of revenues is critical for survival.

Our business objective is to develop a model to profile the customers based on their usage patterns, the activities they indulge in and the preferred handsets in order to design a mobile handset based contract with service plans that will cater to their areas of interest. To realize our business objective, we need to apply unsupervised data mining techniques on given data to bring out clusters of people with similar data-usage attributes and mobile preferences. The clusters, so identified can then be targeted by service providers with customized data plans and contracts.

With more than 25 Mobile service providers in India, all the service providers want to increase their market share as quickly as possible. Few techniques to improve market share can be by good marketing campaigns or by providing customized connection plans and excellent customer service when the customer walks in to the store. In most of the cases, the customer’s interaction with the representative from service provider will determine whether the customer will continue service with that provider or not.

The goal of this project is to build a model for exploring factors effecting a telecommunications firm’s ability to provision circuits