Scalable, Trie-based Approximate Entity Extraction for Real-Time Financial Transaction Screening
This addresses the need for financial institutions to detect terrorism-related entities without disrupting legitimate transactions, but it appears incremental as it builds on existing approximate matching techniques.
The paper tackles the problem of screening financial transactions for terrorism affiliations by presenting a scalable solution that extracts entities from structured and unstructured messages in real time using approximate similarity matching.
Financial institutions have to screen their transactions to ensure that they are not affiliated with terrorism entities. Developing appropriate solutions to detect such affiliations precisely while avoiding any kind of interruption to large amount of legitimate transactions is essential. In this paper, we present building blocks of a scalable solution that may help financial institutions to build their own software to extract terrorism entities out of both structured and unstructured financial messages in real time and with approximate similarity matching approach.