Discovering Experts, Experienced Persons and Specialists for IT Infrastructure Support

Abstract

Workforce analytics (i.e., statistical analysis, modeling and mining of HR data) is particularly important in service industries. Service industries are people-intensive and the knowledge and expertise of the people within an organization is a strategic resource critical for success. Performance of employees in a service organization is directly related to the customer satisfaction and creation of value. In this paper, we adopt a domain-driven data mining approach and begin by raising specific business questions in workforce the analysis with a focus on IT Infrastructure Support (ITIS) services and then propose solutions for them. We distinguish between three aspects of what makes people valuable in an ITIS organization: expertise, specialization and experience. We propose novel formalizations of these notions and discuss rigorous statistical and optimization based algorithms to discover these 3 types of people (along with their work areas). In particular, for the important problem of expert discovery, we propose two separate algorithms: one statistical and another based on data envelopment analysis technique from optimization. The approaches have been implemented and have produced satisfactory results on more than 25 real-life ITIS datasets, one of which we use for illustration. [Service Science, ISSN 2164-3962 (print), ISSN 2164-3970 (online), was published by Services Science Global (SSG) from 2009 to 2011 as issues under ISBN 978-1-4276-2090-3.]