Goal
Accurately extract a dozen of key elements from large number of public companies’ Annual and Quarterly Financial Reports (10Q)
Challenge
Investment banks analyze quarterly financial reports (100) from a long list of public companies that they are interested in investing. For this particular requirement, foreign exchange swaps of varies types need to extracted from the reports, so that the business analysts can take the outputs.
Outcome
Labeled over 2000 individual reports and built a viable machine learning model to extract the information from the summarized files.
Singularity achieved over 98% accuracy for their testing files, which is more accurate than their past human extracted values, and a lot more consistent as well. Consistency is a business value that is above and beyond the cost-saving ROI as stated below.