Restless Bandit

About Restless Bandit

Restless Bandit aggregates tens of millions of resumes and job descriptions annually to build its statistical Talent Rediscovery models, this corpus of data allows for research and investigation into labor market trends. And this data set is overwhelmingly white-collar workers. Specifically, this examination used 19,258,407 resumes. In order to determine industry classifications, the Restless Bandit data science team implemented a vector space model between companies on resumes. By examining millions of resumes, a signal begins to emerge as to which companies are similar. For example: Eli Lilly tends to hire people from within a group of companies such as Merck, Novartis, etc. Companies with a high similarity rating are grouped into an industry segment. While the team has gathered enough data to determine diversity at a company-bycompany level for Global 2000 enterprises, to protect corporate privacy this report will focus on industry segments only.