Investment Banking Cover Letter for a Large Financial Institution

1

Business Analyst

Blurry and Curved

Pill Bottles

4

weeks

100%

Mobile

CHALLENGE Overview

Trade Finance receives unstructured cover letters

Data includes sending bank data and paying bank data

Current solution does not provide high enough accuracy    

Client

Large Financial Institution

Goal

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.

IMPACT