Book page

Enhancing the quality of statistical business registers with scraped data

WIN project training logo

The webinar took place on 24 January 2023 and aimed to inspire and equip participants keen to use web-scraped information to enhance the quality of Statistical Business Registers. The webinar discussed approaches to web scraping business information and the automatic prediction of NACE codes via text mining. The webinar also delivered an overview of the following:

  • Web scraping (generic and specific)
  • An introduction to how to automatically identify enterprise's URLs with search engines results
  • How to link we-scraped third-party data to the business register
  • An introduction to how to apply automatic prediction of NACE codes from web scraped text through the application of text mining classifiers

You can view the slides from the presentation and watch the webinar on our  YouTube channel.

Files