ABSTRACT
The recently launched LinkedIn Salary product has been designed with the goal of providing compensation insights to the world's professionals and thereby helping them optimize their earning potential. We describe the overall design and architecture of the statistical modeling system underlying this product. We focus on the unique data mining challenges while designing and implementing the system, and describe the modeling components such as Bayesian hierarchical smoothing that help to compute and present robust compensation insights to users. We report on extensive evaluation with nearly one year of de-identified compensation data collected from over one million LinkedIn users, thereby demonstrating the efficacy of the statistical models. We also highlight the lessons learned through the deployment of our system at LinkedIn.
- Encyclopedia of Social Measurement, volume 2, chapter Non-Response Bias. Academic Press, 2005.Google Scholar
- BLS Handbook of Methods, chapter 3, Occupational Employment Statistics. U.S. Bureau of Labor Statistics, 2008. http://www.bls.gov/opub/hom/pdf/homch3.pdf.Google Scholar
- NIST/SEMATECH e-Handbook of Statistical Methods. National Institute of Standards and Technology, U.S. Department of Commerce, 2013.Google Scholar
- How to rethink the candidate experience and make better hires. CareerBuilder's Candidate Behavior Study, 2016.Google Scholar
- Job seeker nation study. Jobvite, 2016.Google Scholar
- Glassdoor introduces salary estimates in job listings, February 2017. https://www.glassdoor.com/press/glassdoor-introduces-salary-estimates-job-listings-reveals-unfilled-jobs-272-billion/.Google Scholar
- Overview of BLS statistics on pay and benefits, February 2017. https://www.bls.gov/bls/wages.htm.Google Scholar
- Payscale data & methodology, February 2017. http://www.payscale.com/docs/default-source/pdf/data_one_pager.pdf.Google Scholar
- D. Agarwal, R. Agrawal, R. Khanna, and N. Kota. Estimating rates of rare events with multiple hierarchies through scalable log linear models. In KDD, 2010. Google ScholarDigital Library
- J. Bethlehem. Selection bias in web surveys. International Statistical Review, 78(2), 2010.Google ScholarCross Ref
- M. Callegaro, K. L. Manfreda, and V. Vehovar. Web survey methodology. Sage, 2015.Google Scholar
- A. Duerr and S. K. Kancha. Bringing salary transparency to the world. LinkedIn Engineering Blog, 2016. https://engineering.linkedin.com/blog/2016/10/bringing-salary-transparency-to-the-world.Google Scholar
- R. T. Fielding. Architectural styles and the design of network-based software architectures. PhD thesis, University of California, Irvine, 2000. Google ScholarDigital Library
- R. M. Groves, F. J. Fowler Jr, M. P. Couper, J. M. Lepkowski, E. Singer, and R. Tourangeau. Survey methodology. John Wiley & Sons, 2011.Google Scholar
- S. Harris. How to make the job market work like a supermarket. LinkedIn Pulse, 2016. https://www.linkedin.com/pulse/how-make-job-market-work-like-supermarket-seth-harris.Google Scholar
- M. Hubert and E. Vandervieren. An adjusted boxplot for skewed distributions. Computational statistics & data analysis, 52(12), 2008. Google ScholarDigital Library
- R. J. Jessen. Statistical survey techniques. John Wiley & Sons, 1978.Google Scholar
- K. Kenthapadi, A. Chudhary, and S. Ambler. LinkedIn Salary: A system for secure collection and presentation of structured compensation insights to job seekers. In IEEE PAC, 2017. Available at https://arxiv.org/abs/1705.06976.Google ScholarCross Ref
- M. Pinkovskiy and X. Sala-i Martin. Parametric estimations of the world distribution of income, 2009. Working Paper No. 15433, National Bureau of Economic Research.Google ScholarCross Ref
- R. Sandler. Introducing LinkedIn Salary?: Unlock your earning potential. LinkedIn Blog, 2016. https://blog.linkedin.com/2016/11/02/introducing-linkedin-salary-unlock-your-earning-potential.Google Scholar
- R. Sumbaly, J. Kreps, L. Gao, A. Feinberg, C. Soman, and S. Shah. Serving largescale batch computed data with project Voldemort. In FAST, 2012. Google ScholarDigital Library
- J. Weiner. The future of LinkedIn and the Economic Graph. LinkedIn Pulse, 2012.Google Scholar
- L. Zhang and D. Agarwal. Fast computation of posterior mode in multi-level hierarchical models. In NIPS, 2009. Google ScholarDigital Library
Index Terms
- Bringing Salary Transparency to the World: Computing Robust Compensation Insights via LinkedIn Salary
Recommendations
Investigating the Determinants of Starting Salary of IT Graduates
The starting salary of a fresh graduate is considered a potential indicator of career advancement. Yet few studies have examined the determinants of starting salaries of information technology (IT) graduates. Further, existing studies have focused on ...
Exploring the status of the turnover and salary of information technology professionals in Singapore
SIGCPR '93: Proceedings of the 1993 conference on Computer personnel researchThe rapid growth of technology in Singapore and the shortage of IT professionals had an impact on the country's competitiveness. The study shows that the turnover rate among IT professionals is still high, particularly among software professionals. ...
Comments