ESCO for big data analyses

With the digitisation of labour market and education and training processes, more and more big data sources that contain information on occupations, knowledge, skills, competences and related concepts become available. This includes in particular large data sets of job vacancies, CVs, professional profiles, learning opportunities and education or training curricula. Online tools and services such as EURES, Europass, the EU Skills Panorama, public and private job boards collect such data.

Using big data in labour market intelligence

Labour market intelligence (LMI) includes skills analysis and forecasts which enable us to better understand the skills gaps and to align skills supply and demand on the labour market. It is an essential source of information for policy makers, employment service and guidance professionals, education and training providers, employers, jobseekers and learners.

However, traditional LMI has several shortcomings. Data collection involves high costs, it lacks behind developments in the labour market and it is often not detailed enough to understand skills gaps in the labour market. Real-time labour market information (RLMI) uses big data analysis to overcome these shortcomings. It uses information sources that can be exploited instantly. It relies heavily on big data analysis of the information that is available online in the labour market, in particular in job vacancies, making the best possible use of advances in technology. The European Centre for the Development of Vocational Training (Cedefop) is currently testing RLMI in a pilot project using ESCO.

Using big data to improve ESCO

Big data sources can also be used for the continuous improvement of ESCO. They can be a useful source when updating ESCO. Of course, legal constraints always need to be verified before any use of big data sources. Analysing big data allows the ESCO team to detect, evaluate, and interpret data deriving from the education and labour market. It can be repeated on a regular basis and at low incremental costs. The relevant data can be analysed and compared with the data of the ESCO classification to identify any mismatches and missing terminology that could derive from new occupations and skills requirements.