A Data-Driven Analysis of Employee Development Based on Working Expertise

Abstract

Employees' expertise is the basic component of human capital of organizations. As the role of human capital and the understanding of employee development become increasingly vital, research works about the effects of working expertise on development are necessary. This article aims to confirm the effect of expertise and find out how expertise affects development. In this article, we analyze employee development and working expertise through data-driven methods, using a data set of a Chinese state-owned enterprise. In addition to statistical analysis, expertise networks are constructed to discover more insights about the effect of expertise on employee development. Moreover, to further validate and exploit the effect, a prediction model of development potential is proposed based on machine learning. Results of the experiment show that the random forests model with network embedding (RFNE) is effective in identifying excellent employees. Finally, with the help of data-driven analysis of expertise and development, we find that the appropriate post, the right choice, the distinctive competency, as well as the interdisciplinary transfer contribute to employee development.