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
- $750K in annual savings based on reduction in errors and efficiency.
- Achieving more while working with less samples – faster, more accurate, and efficient.
- Increasing straight through processing (STP) to 91%+.
- Results in 24 hours
