Investment Banking Cover Letter for a Large Financial Institution
Blurry and Curved
Trade Finance receives unstructured cover letters
Data includes sending bank data and paying bank data
Current solution does not provide high enough accuracy
Large Financial Institution
Streamlining error-prone, manual review of unstructured cover letters
WHAT WE DID
- The model was able to index and classify documents at the field level, solving the problems of errors and manual review.
- Classify and extract data from cover letters, routing exceptions to staff. Each manual intervention improves the completeness and confidence of AYR’s machine learning models, which makes the platform smarter and more accurate.
- Model training with 62 samples from 3 banks. 95% accuracy was achieved in 24 hours to extract key data from cover letters.