EXTRACTING INFORMATION FROM DOCUMENTS
Problem
Companies have specific departments that are used for copying and pasting information from physical documents into structured digital data. This is a process that requires a lot of time, resources, and money.
Solution
A specific platform was created, using a machine learning model which receives scanned documents and extracts the needed information from them, storing them into specific tables in a system used by the client.
Results
After a specific test period, the model provided an accuracy of 80%. This percentage provides better results than manually copying data from physical documents into software because of the misspells that people usually do.