Collapsing Corporate Confusion Leveraging Network Structures for Effective Entity Resolution in Relational Corporate Data
12 Pages Posted: 16 Oct 2017
Date Written: October 12, 2017
In this paper, we introduce a novel battery of classifiers to resolve inconsistencies among entity names within large corporate datasets. Using data on the corporate sector, we describe our relational approach to entity resolution, and the problems in existing approaches it serves to address. We leverage the relational structure of BoardEx employment data to test the efficacy of these classifiers using a ground-truth sample of coded name inconsistencies. We show that these classifiers accurately resolve such inconsistencies, and further show the effect of this resolution on network topology. We conclude with implications for existing findings and steps for future work.
Keywords: entity resolution, network methods, corporate data, BoardEx
Suggested Citation: Suggested Citation