About a-team Marketing Services
The knowledge platform for the financial technology industry
The knowledge platform for the financial technology industry

A-Team Insight Blogs

Observational Learning Boosts Data Quality, Improves Reconciliations, Cuts Costs of Exceptions

Subscribe to our newsletter

Large data volumes and manual data validation techniques are making it difficult for firms to achieve levels of data quality required to support seamless transaction processing and regulatory reporting. The problem is exacerbated by MiFID II and other emerging regulations that impose new processes on transaction reporting, including reconciliation of transactions from the trade repository against front-office records.

A solution to the problems of poor data quality and hence poor reconciliations lies in observational learning, a form of AI that learns by mimicking human behaviour and could, according to early indications, greatly reduce reconciliation exceptions and provide significant cost savings.

By applying observational learning disciplines to regulatory reporting, analysts at SmartStream Technology’s Innovation Lab in Vienna have completed proofs of concepts (POCs) with two major banks that succeeded in accelerating the exceptions management process while rapidly and vastly improving data quality. The result was a sustained reduction in error rates and an accompanying drop in operational costs associated with reconciliations in trade and transaction reporting.

SmartStream’s approach, which is detailed in an A-Team Group white paper Deploying Observational Learning for Improved Transaction Data Quality, took the concept of observational learning and applied it to exceptions management algorithms as part of its Affinity AI offering. This allowed Affinity to observe human data verification processes, capture and ‘understand’ them, and ultimately make recommendations for future exceptions.

The results of the POCs, which included Affinity observational learning within SmartStream’s Air cloud native reconciliations platform, show cost savings of at least 20%, with one participant in a PoC recording savings of $20 million. Download the white paper to find out how your organisation could benefit from observational learning.

Subscribe to our newsletter

Related content

WEBINAR

Recorded Webinar: Mastering Data Lineage for Risk, Compliance, and AI Governance

Financial institutions are under increasing pressure to ensure data transparency, regulatory compliance, and AI governance. Yet many struggle with fragmented data landscapes, poor lineage tracking and compliance gaps. This webinar will explore how enterprise-grade data lineage can help capital markets participants ensure regulatory compliance with obligations such as BCBS 239, CCAR, IFRS 9, SEC requirements...

BLOG

Clearwater Looking to Bridge Front-to-Back Office Tech Gaps with Acquisitions

It’s difficult for data and technology companies to fully service financial institutions’ front-to-back operations when behemoth providers are offering closely integrated capabilities at scale already. Clearwater Analytics, however, has a strategy that it believes will work not by necessarily competing with the big aggregators, but by working with them and filling gaps that they don’t...

EVENT

TradingTech Summit London

Now in its 14th year the TradingTech Summit London brings together the European trading technology capital markets industry and examines the latest changes and innovations in trading technology and explores how technology is being deployed to create an edge in sell side and buy side capital markets financial institutions.

GUIDE

Regulatory Data Handbook 2025 – Thirteenth Edition

Welcome to the thirteenth edition of A-Team Group’s Regulatory Data Handbook, a unique and practical guide to capital markets regulation, regulatory change, and the data and data management requirements of compliance across Europe, the UK, US and Asia-Pacific. This year’s edition lands at a moment of accelerating regulatory divergence and intensifying data focused supervision. Inside,...