AI Research
The AI group has a mission of building the next-gen RiskOps AI to safeguard businesses and people from fraud and financial crime that is responsible and explainable by design. The group aims to reimagine financial services, risk management and financial crime prevention through the lens of state-of-the-art Human-Centered AI and propose product solutions to significant problems, such as identity, detection, and automation, while mitigating bias and promoting transparency.
Research Focus:
- AI in Financial Services
- AutoML
- AI safety, fairness, privacy, robustness
- ML Monitoring, Explainability and Observability
- Deep Learning & Network Science
Recent Publications
Rethinking XAI Evaluation: A Human-Centered Audit of Shapley Benchmarks in High-Stakes Settings
Published at NeurIPS 2026 Evaluations and Datasets Track
Related Blog Posts
The GANfather: Using Malicious GenAI Agents to Combat Money Laundering
Digital systems have become deeply integrated into many aspects of modern life, particularly within the financial sector. While digital banking simplifies day-to-day operations for clients, it also creates new opportunities for malicious actors to exploit these systems.
Ricardo Ribeiro Pereira
Aequitas Flow step-by-step: a Fair ML optimization framework
In this blog post we will visit Aequitas Flow, an Open-Source framework designed to run complete and standardized experiments of Fair ML algorithms. We encourage you to try Aequitas Flow with the Google Colab Notebooks, which are available in the project’s GitHub repository.
Sérgio Jesus
The GANfather: Using Malicious GenAI Agents to Combat Money Laundering
Digital systems have become deeply integrated into many aspects of modern life, particularly within the financial sector. While digital banking simplifies day-to-day operations for clients, it also creates new opportunities for malicious actors to exploit these systems.
Ricardo Ribeiro Pereira
Aequitas Flow step-by-step: a Fair ML optimization framework
In this blog post we will visit Aequitas Flow, an Open-Source framework designed to run complete and standardized experiments of Fair ML algorithms. We encourage you to try Aequitas Flow with the Google Colab Notebooks, which are available in the project’s GitHub repository.
Sérgio Jesus
Page printed in 12 Oct 2026. Plase see https://research.feedzai.com/research_area/ai-research for the latest version.