We explore the use of online job postings as an innovative complementary source of labour
demand statistics. The paper concentrates on new developments in the area, including the
usage and validation of online data sources, trends, biases and caveats of the data
generation and data extraction process. We provide detailed explanations of the data
cleansing and data preparation process which proves to be useful for anyone working with
raw online data sources. We explore the general data pipeline underpinning continuous
data mining and data utilization, that could be beneficial for any organization building its
own online data analysis process. We provide detailed discussions of the design of the
skills extraction process using word2vec model. We discuss the application of the model
and explore some of the skills analysis methods and visualizations, such as job titles,
salaries, frequent skills histograms, skills correlation scatterplots, graph analysis of skills
co-occurrence, UK regional skills analysis. We applied regression analysis, outlining
various effects of person competencies on the salary. We conclude that online job postings
provide rich and extensive insights into the labour market and can complement the official
statistics.
