PROJECT TITLE :

Mining Competitors from Large Unstructured Datasets - 2017

ABSTRACT:

In any competitive business, success is predicated on the ability to form an item more appealing to customers than the competition. A variety of queries arise within the context of this task: how do we have a tendency to formalize and quantify the competitiveness between two items? Who are the most competitors of a given item? What are the features of an item that the majority affect its competitiveness? Despite the impact and relevance of this problem to several domains, solely a limited amount of work has been devoted toward an effective resolution. In this paper, we tend to gift a proper definition of the competitiveness between 2 things, based mostly available segments that they'll each cowl. Our analysis of competitiveness utilizes customer reviews, an abundant source of information that is out there during a wide selection of domains. We gift efficient strategies for evaluating competitiveness in massive review datasets and address the natural problem of finding the top-k competitors of a given item. Finally, we have a tendency to evaluate the quality of our results and therefore the scalability of our approach using multiple datasets from totally different domains.