• Workshops
  • JournoCon 2020
  • DDJ Tools
  • Dictionary
  • Projects
  • Events
Journocode_
WorkshopsAbout Us

OpenSchufa: Three things we’ve learned from parsing 2800 credit reports

  • Blog
  • Git
  • Guest posts
by Journocode on October 21, 2019 0 Comments
OpenSchufa: Three things we’ve learned from parsing 2800 credit reports

Marcel Pauly, his colleagues from SPIEGEL Data and BR Data evaluated reports from Schufa, the most influential credit agency in Germany. The documents were provided by 2800 volunteers in a crowdsourcing project. Some documents came scanned, some were photographed. It was an OCR nightmare.

A guest post by Marcel Pauly

Read More

Join us on Slack

Recent Posts

  • JournoCon 2020 is here! (German post)
  • Squirrel wishlist 2020: Tell us what you need from Journocode
  • OpenSchufa: Three things we’ve learned from parsing 2800 credit reports

Archives

Categories

Meta

  • Log in
  • Entries RSS
  • Comments RSS
  • WordPress.org

Pages

  • About Us
  • Events
  • Imprint
  • Data journalism tool collection
  • Data Journalism Dictionary
  • Privacy Policy
  • Privacy Policy
Privacy & Cookies: This site uses cookies. By continuing to use this website, you agree to their use.
To find out more, including how to control cookies, see here: Cookie Policy
Info

Imprint

Privacy policy

Contact

facebook: facebook.com/journocode
twitter: twitter.com/journocode
e-mail: contact@journocode.com

Copyright © 2021 Journocode.