Two-stage graph-clustering algorithm and localised classification model to identify apt business locale Online publication date: Mon, 31-Aug-2015
by Harya Widiputra; Marsudi Kisworo; Agnes Novita; Tiolina Pardede
International Journal of Business Information Systems (IJBIS), Vol. 20, No. 2, 2015
Abstract: Previous studies conducted in the economy, finance and business management fields have found that there exists a collection of business agglomerations, which contain various numbers of firms that are spread on a specific region. Based on this realness, the selection of apt business locale for a new establishment should then be considered as a trial to identify the prospective business agglomeration in which the new establishment would be able to compete with existing firms. Consequently, a pertinent method that works by characterising the business agglomerations from a collection of business firm's data and subsequently computes the projection of business performance level of a new establishment in each identified agglomeration is developed in this study. A two-stage graph-clustering algorithm that purposively designed to unravel the task of business agglomerations identification is introduced, whereas the localised classification models perform the prediction of business performance level in each known agglomerations. Decisively, results from conducted experiment suggest that the proposed method is beneficial to distinguish the apt business locale for new establishments in a particular region with a collection of business agglomerations.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Business Information Systems (IJBIS):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com