Title: Efficient microarea selection algorithm for infrastructure installation of broadband services

Authors: Motoi Iwashita; Akiya Inoue; Takeshi Kurosawa; Ken Nishimatsu

Addresses: Department of Management Information Science, Chiba Institute of Technology, 2-17-1 Tsudanuma, Narashino-shi, Chiba 275-0016, Japan ' Department of Management Information Science, Chiba Institute of Technology, 2-17-1 Tsudanuma, Narashino-shi, Chiba 275-0016, Japan ' Department of Mathematical Information, Tokyo University of Science, 1-3 Kagurazaka, Shinjuku-ku, Tokyo 162-8601, Japan ' Network Technology Laboratories, NTT, 3-9-11 Midori-cho, Musashino-shi, Tokyo 180-8585, Japan

Abstract: The diffusion of broadband services based on wired/wireless networks has been an important issue for a long time. Since the installation of such networks requires a large amount of time and money, low-usage facilities can cause problems for business in terms of investment efficiency. Therefore, the estimation of the potential demand for such networks in different areas, particularly microareas such as municipal areas across the nation, and the formulation of a microarea selection rule for the installation of the network infrastructure are absolutely necessary. In this paper, we propose a microarea selection algorithm that uses commuting flows among microareas as the broadband service propagation model. We have empirically and analytically evaluated the proposed algorithm, and the results have revealed that this method is very effective, particularly for the early stage of the infrastructure installation of broadband services.

Keywords: data mining; area marketing; demand forecast; decision support system; algorithm; customer behaviour; service diffusion; innovation diffusion.

DOI: 10.1504/IJCISTUDIES.2016.083571

International Journal of Computational Intelligence Studies, 2016 Vol.5 No.3/4, pp.219 - 236

Received: 15 Sep 2015
Accepted: 09 Jan 2016
Published online: 11 Apr 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article