Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

11-2017

Abstract

Analyzing job hopping behavior is important for theunderstanding of job preference and career progression of working individuals.When analyzed at the workforce population level, job hop analysis helps to gaininsights of talent flow and organization competition. Traditionally, surveysare conducted on job seekers and employers to study job behavior. While surveysare good at getting direct user input to specially designed questions, they areoften not scalable and timely enough to cope with fast-changing job landscape.In this paper, we present a data science approach to analyze job hops performedby about 490,000 working professionals located in a city using their publiclyshared profiles. We develop several metrics to measure how much work experienceis needed to take up a job and how recent/established the job is, and thenexamine how these metrics correlate with the propensity of hopping. We alsostudy how job hop behavior is related to job promotion/demotion. Finally, weperform network analyses at the job and organization levels in order to deriveinsights on talent flow as well as job and organizational competitiveness.

Keywords

Career progression, Flow network, Gain insight, Job seekers, Job-hopping, Population levels, Work experience, Working professionals, Data mining

Discipline

Computer Sciences | Databases and Information Systems | Numerical Analysis and Scientific Computing

Research Areas

Data Science and Engineering

Publication

17th IEEE International Conference on Data Mining Workshops ICDMW 2017: New Orleans, November 18-21: Proceedings

First Page

207

Last Page

214

ISBN

9781538614808

Identifier

10.1109/ICDMW.2017.172

Publisher

IEEE

City or Country

Piscataway, NJ

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1109/ICDMW.2017.172

Download

Share

COinS