Solution
FinTrU developed TrU Label, a highly
configurable document intelligence solution
designed to automate data extraction from
large, complex regulatory documents.
To bring this to life, FinTrU partnered
with ABBYY, integrating its advanced
optical character recognition (OCR) and
intelligent document processing (IDP)
technologies directly into TrU Label. This
allowed FinTrU to focus on its proprietary
machine learning models and product
differentiators, rather than building the full
document recognition stack from scratch.
TrU Label includes pre-trained options for common regulatory use cases such as KYC, credit risk, and
ISDA contract. With ABBYY’s IDP platform powering the document ingestion and data extraction layer,
TrU Label was able to:
- Classify more than 54 types of capital markets documents.
- Extract more than 60 key data fields from complex financial documents using FinTrU’s industry-specific data model.
- Enable human-in-the-loop validation through a maker-checker workflow, where AI prefills information, a first reviewer verifies it, and a second reviewer confirms it for compliance.
- Produce audit-ready, annotated PDFs and clean, structured data that can integrate directly into bank systems, complete with data lineage for auditability.
FinTrU launched the platform with a multinational bank in late 2023. Since then, the automation engine
has been delivering remarkable results.