Title: A fuzzy prediction model for calling communities

Authors: Keivan Kianmehr, Reda Alhajj

Addresses: Department of Computer Science, University of Calgary, Calgary, Alberta, Canada; Department of Computer Science, Global University, Beirut, Lebanon. ' Department of Computer Science, University of Calgary, Calgary, Alberta, Canada; Department of Computer Science, Global University, Beirut, Lebanon

Abstract: The analysis of logs related to social communities has recently received considerable attention for its importance in shedding light on social concerns by identifying different groups, and hence helps in resolving issues like predicting terrorist groups. In general, identifying calling communities can be used to determine a particular customer|s value according to the general pattern of behaviour of the community that the customer belongs to; this helps in creating an effective targeted marketing design, which is significantly important for increasing profitability. In the telecommunications industry, machine-learning techniques have been applied to the Call Detail Record (CDR) for predicting customer behaviour such as churn prediction. In this paper, we pursue the identification of the calling communities and demonstrate how cluster analysis can be used to effectively identify communities using information derived from the CDR data. We use the information extracted from the cluster analysis to identify customer calling patterns. Customer calling patterns are then input to a classification algorithm to generate a classifier model for predicting the calling communities of a customer. We apply two different classification methods: the Support Vector Machine (SVM) algorithm and the fuzzy genetic classifier. The latter method is used for possibly assigning a customer to different classes with different degrees of membership. The reported test results demonstrate the applicability and effectiveness of the proposed approach.

Keywords: classification; clustering; support vector machines; SVM; fuzzy genetic classifiers; fuzzy prediction; calling communities; social concerns; terrorists; terrorism; behaviour patterns; targeted marketing; profitability; telecommunications industry; machine learning techniques; call detail records; churn predictions; cluster analysis; CDR data; customer calling patterns; classification algorithms; class assignment; membership degrees; networks; virtual organisations; web based organisations; online organisations; open source intelligence; web mining; world wide web; internet.

DOI: 10.1504/IJNVO.2011.037162

International Journal of Networking and Virtual Organisations, 2011 Vol.8 No.1/2, pp.75 - 97

Available online: 30 Nov 2010 *

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