Skip to content
THE CHALLENGE
A time-sensitive 18-month transaction investigation that would have taken months of full-time staff at a substantial cost and varying quality using traditional means was completed with a consistent, analytics-driven review methodology.
THE SOLUTION
Data Cleansing: The original data provided by the bank were incomplete and noisy. To separate noise from useful information, we undertook a cleansing exercise prior to starting the analysis. We applied advanced analytics, pattern analysis, and indicator analysis to organize, deduplicate and consolidate data.
Transaction Analysis Using Machine Learning Models: After developing product-specific scenarios using our industry expertise, we leveraged machine learning to rank data in certain categories and applied a random forest model to conduct preliminary reviews. We incorporated entity-level diligence information using DDIQ as a model input to enhance associated party risk considerations.
Analytics-Driven Reviews of Unstructured Trade Data: To review more than 3,000 trade finance transactions for red flags as part of the lookback, we leveraged OCR and pattern recognition technology to help screen information within nearly 100,000 associated documents for sanctions hits and trade finance red flags.
Manual Adjudication Supplement: Finally, we used our team to perform a manual analysis on the flagged transactions.
