Automatic Discovery of Emerging Trends using Cluster Name Synthesis on User Consumption Data: Extended Abstract.

A business problem for the telecommunication companies is to provide an appropriate promotional coupon to suitable customers. This problem leads to the challenge of identifying behavioral patterns of customers and deliver the right customer engagement at the right time. So there is a need for a system that can enable the telecommunication companies to go for the best marketing strategy by leveraging customer intelligence to drive offer acceptance based on personas. Technically it is possible for the telecommunication companies to recommend suitable advertisements if they can classify the web sites browsed by their customers into classes like sports, e-commerce, social networking, streaming media etc. Another problem is to classify a new website when it doesn't belong to any of the existing clusters. In this paper, the authors are going to propose a method to automatically classify the websites and synthesize the cluster names in case it doesn't belong to any of the predefined clusters. We have experimented on a small set of data set and the classification results are quite convincing. Moreover, the phrases used to describe a website if it doesn't belong to existing classes are compliant to the phrases obtained from manual annotation. This proposed system uses the Wikipedia data to construct the document for the websites browsed by the customers.