The use of data mining techniques to predict the ranking of E-government services

Abstract

The usage and improvement of information and communication technologies to enhance public sector services (e-Government) was recognized as an important task for the majority of governments in developed countries. Several countries are working hard to improve their e-Government ranking to support their sustainable development. This study employed several data mining techniques to build models that can adequately predict the e-Government ranks of 192 United Nation countries and identify the factors that affect those ranks. Our analysis and results show that the attributes the UN uses to rank countries are well conceptualized and, therefore, we were able to accurately predict the e-Government ranking of the countries involved using supervised learning (classification) and supervised learning (regression). The analysis also shows that e-Government and telecommunication infrastructure index, fixed telephone subscriptions, Internet usage, human capital, and online service index are the most important factors in e-Government ranking.