Yields.io
Founded in 2017 in Ghent, Yields.io builds software for model risk management (MRM) in financial institutions. As banks increasingly rely on AI and machine learning models for credit scoring, fraud detection, and trading, regulatory bodies require formal validation, documentation, and ongoing monitoring of those models. Yields.io automates this compliance workflow.
The platform supports the full model lifecycle: inventory management, validation workflows, performance monitoring, and regulatory reporting aligned with frameworks such as SR 11-7 and ECB model risk guidelines. With EUR 6M+ from Volta Ventures, the company is positioned at the intersection of AI governance and financial regulation.
Yields.io is part of the Ghent AI and Fintech cluster and addresses a governance gap that grows more acute as financial AI deployments multiply.
Funding History
EUR 6M+ from Volta Ventures
Key People
Jos Gheerardyn - co-founder, ceo
In the media3
Jos Gheerardyn discusses how data drives value through visualization for pattern discovery and algorithmic learning, using examples like DeepMind's AlphaZero to illustrate how algorithms learn from data. He explains how incomplete or incorrect data can cause problems in machine learning models, such as his roomba example where missing sensor data led to unexpected behavior, and emphasizes that managing data quality is essential for sustainable model operation since data-related risks are a major component of operating models.
Jos Gheerardyn discusses how 2026 will require scaled AI governance due to rapid evolution of AI tools and increasing use cases, necessitating automated and differentiated governance approaches across models with varying risk levels. He emphasizes that AI should assist rather than replace human decision-making in model validation, help identify documentation weaknesses, and support real-time monitoring since traditional periodic review cycles are insufficient for quickly-built AI systems.
Jos Gheerardyn discusses how automating model validation faces operational rather than technical challenges, particularly because different types of models require different standardization approaches that are difficult to align across organizations. He explains that the growth of AI use cases, driven by multiple contexts for single AI systems and customizable AI tools, increases governance complexity, and proposes that multi-governance model risk management with better domain modeling can reduce unit costs and maintenance effort by decomposing redundant model-usage combinations.