Fighting against fraud with AI for business verification

Posted on May 12, 2024 by Editor

In an increasingly online world, the need to verify legal entities accurately is paramount. Enter artificial intelligence (AI), a transformative technology that holds the promise of automating entity verification and monitoring, thereby reducing the risk of fraud and criminal activities. Damian Borth, Professor of Artificial Intelligence & Machine Learning at the University of St. Gallen, recently completed a project with GLEIF exploring how AI can boost legal-entity verification. In a recent blog post, he shed light on how leveraging open, standardised and high-quality legal-entity data within AI models can enhance financial safety.

AI and machine learning technologies offer a game-changing solution to anti-money laundering (AML) challenges. By analysing vast datasets, they can detect complex patterns and anomalies, significantly enhancing the detection of suspicious transactions. Professor Borth’s recent collaboration with GLEIF resulted in an AI model capable of accurately predicting an entity’s legal form using its name and jurisdiction, showcasing AI’s potential to enhance the reliability of business data.

Combining AI technology with high-quality data offers the best results. Professor Borth outlines how open, reliable, standardised and high-quality data is foundational for successful AI development. Standardised data ensures that AI models are trained on accurate information, leading to more effective outcomes.

Structured data, such as the data on legal entities provided by the Legal Entity Identifier (LEI), enriches AI research by providing a consistent dataset for training and testing AI models in financial and legal contexts. This uniformity improves model reliability and interoperability across jurisdictions and improves the AI model’s decision-making abilities.

GLEIF’s recent project demonstrates how harnessing the synergy between AI and structured data holds serious potential for business reporting. By utilising existing pools of structured data, we can build more useful, accurate AI models that contribute to financial safety and transparency.

For more insights, read the interview here.

Other Posts


Would you like
to learn more?

Join our Newsletter mailing list to
stay plugged in to the latest
information about XBRL around the world.

By clicking submit you agree to the XBRL International privacy policy which can be found at xbrl.org/privacy