Garasto, Stef, Djumalieva, Jyldyz, Kanders, Karlis, Wilcock, Rachel and Sleeman, Cath (2021) Developing experimental estimates of regional skill demand. Discussion Paper. National Institute of Economic and Social Research, London.

Preview

PDF (Author's published report) 36300_GARASTO_Developing_experimental_estimates.pdf - Published Version Available under License Creative Commons Attribution No Derivatives. Download (1MB) | Preview

Abstract

This paper shows how novel data, in the form of online job adverts, can be used to enrich official labour market statistics. We use millions of job adverts to provide granular estimates of the vacancy stock broken down by location, occupation and skill category. To derive these estimates, we build on previous work and deploy methodologies for a) converting the flow of job adverts into a stock and b) adjusting this stock to ensure it is representative of the underlying economy. Our results benefit from the use of duration data at the level of individual vacancies. We also introduce a new iteration of Nesta’s skills taxonomy. This is the first iteration to blend an expert-derived collection of skills with the skills extracted from job adverts. These methodological advances allow us to analyse which skill sets are sought by employers, how these vary across Travel To Work Areas in the UK and how skill demand evolves over time. For example, we find that there is considerable geographical variability in skill demand, with the stock varying more than five-fold across locations. At the same time, most of the demand is concentrated among three categories: “Business, law & finance”, “Science, manufacturing & engineering” and “Digital”. Together, these account for more than 60% of all skills demanded. The type of intelligence presented in this report could be used to support both local and national decision makers in responding to recent labour market disruptions.

Item Type:	Monograph (Discussion Paper)
Uncontrolled Keywords:	big data; labour demand; online job adverts; skills; word embeddings; machine learning
Subjects:	H Social Sciences > HA Statistics H Social Sciences > HD Industries. Land use. Labor > HD28 Management. Industrial Management Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Faculty / School / Research Centre / Research Group:	Faculty of Education, Health & Human Sciences Faculty of Engineering & Science Faculty of Engineering & Science > School of Computing & Mathematical Sciences (CMS)
Last Modified:	26 May 2022 16:51
URI:	http://gala.gre.ac.uk/id/eprint/36300

Actions (login required)

View Item

Downloads