Data mininig application to predict customer churn

Abstract

This report is being submitted towards PGSM curriculum requirement of end term project. This section provides brief overview of the project and results obtained. Problem Definition During the past 5 years wireless industry has been one of the fastest growing businesses in the economy. The number of subscribers doubled every two years during the 90's. As per Business Week 2002, Wireless News Factor 2002, • By 2003, 25% of all telephone minutes will be accounted for by wireless services. • By 2006, the US penetration in the wireless-voice market is expected to hit 189 million subscribers, while that of the wireless-data market is expected to jump to 38 million subscribers. • Of all wireless customers, 70% are using digital networks that allow carriers to efficiently offer more appealing services. • Investment in network infrastructure has increased by 17% and the number of cell sites increased by 22.3%, indicating a clear upward trend in US coverage and quality. • Industry is consolidation - From nearly 60 operators to now 6 major operators accounting for 80% of the business. • Tapered growth - From 50% annual growth has been reduced to 15-20% in 2002, and it is expected to come down to 10% in 2003. • Competition - To the benefit of consumer, heavy competition resulted in price wars. • Churn - changing over to competitors. Industry average churn rate has been between 20-25%.