Labor markets around the world are currently experienc- ing a perplexing quandary: high levels of unemploy- ment or underemployment while job openings are at a
record level. A recent report1 from McKinsey discussed how
employers in major European economies are facing a growing crisis of not finding people with the necessary skills to fill
even entry-level positions. At the same time, the European
Union has 5.6 million young people without jobs. Similarly,
in the U.S., a recent Labor department report2 showed that
there were a record number of job openings. Although the
U.S unemployment rate is less than 5 percent, there has also
been an increase in the number of underemployed workers.
While some employers have outsized expectations for basic
entry-level jobs, the primary reason for persistently high levels of job openings is the skills gap. A recent study found that
up to 80 percent of the engineers in India were unemployable3 because engineering colleges were not teaching skills
applicable in the industry. The skills gap can pose socioeconomic challenges for an economy: persistently high (youth)
unemployment and loss in profits for companies can seriously hinder economic growth. To analyze and close the
skills gap, it is imperative to have an automated system that
can leverage a skills taxonomy to accurately detect skills in
human capital data such as resumes and job ads. The resulting data forms the foundation for labor market analysis and
consequently facilitates reskilling and workforce training
programs. Automated skill systems can also be used in job
matching and recommendation systems to better match candidates to jobs and reduce unemployment. Such skill systems
Large-Scale Occupational
Skills Normalization for
Online Recruitment
Phuong Hoang, Thomas Mahoney, Faizan Javed, Matt McNair
; Job openings often go unfilled despite
a surfeit of unemployed or underemployed workers. One of the main reasons for this disparity is a mismatch
between the skills required by employers
and the skills that workers possess. This
mismatch, also known as the skills gap,
can pose socioeconomic challenges for
an economy. A first step in alleviating
the skills gap is to accurately detect
skills in human capital data such as
resumes and job ads. Comprehensive
and accurate detection of skills facilitates analysis of labor market dynamics. It also helps bridge the divide
between supply and demand of labor by
facilitating reskilling and workforce
training programs. In this article, we
describe SKILL, a named entity normalization (NEN) system for occupational
skills. SKILL is composed of ( 1) a skills
tagger, which uses properties of semantic word vectors to recognize and normalize relevant skills, and ( 2) a skill
entity sense disambiguation component, which infers the correct meaning
of an identified skill. We discuss the
technical design and the synergy
between data science and engineering
that was required to transform the system from a research prototype to a production service that serves customers
from across the organization. We also
discuss establishing customer feedback
loops, which led to improvements to the
system over time. SKILL is currently
used by various internal teams at
CareerBuilder for big data workforce
analytics, semantic search, job matching, and recommendations.