A challenge from KPMG for our datascientist trainning at BeCode.
Scrap data and status from a maximum of enterprises in Belgium.
- Then, extract meta-data.
- Then, for the scanned documents, extract the text with some OCR.
- Then, if the document is not in english, translate it.
- Then, identify articles.
- Then, classify them.
- Then, put everythink in a database.
This project is production-ready. You can try it there: https://elegant-goodall-6abe26.netlify.com/