Examining categorization of Telecom Circles in India using unsupervised k-means clustering on techno-economic indicators

Abstract

The promulgation of the first National Telecom Policy of India in the year 1994 resulted in the geographical segregation of the country into 22 administrative units referred to as Telecom Circles (TCs). The creation of TCs was to enable targeted policy formulation and smooth implementation of the policy objectives of the government. The TCs were further clustered into four different categories, namely Metro, category A, category B, and category C, each category signaling to the telecom service providers the unique market characteristics and the Teledensity potential of the region. We attempt to reexamine today the rationale behind this unique policy experiment using an unsupervised k-means clustering technique. We identify Human Development Index, Gross Domestic Product, and Teledensity indicators to be the suitable parameters for clustering the TCs now. Interestingly, this time too, the clustering analysis suggests four categories only to be suitable for India’s case. Subsequently, a fresh TC allocation exercise, based on clustering, recommends only a few re-assignments of TCs to different categories. Thus, the results largely validate the currently existing framework of TC categorization in the country without finding the need for any major overhaul.