Descubra Feedzai Research
Investigación aplicada para producir el mejor producto de mitigación de riesgos financieros del mundo.
No solo construimos modelos. Nutrimos el entorno en el que pueden adaptarse más rápido, proteger a los clientes de manera más sólida y revelar sombras al instante en la red financiera global.
Publicaciones recientes
Causal Discovery on Irregular Time Series
Causal discovery methods have shown strong performance in temporal systems, but they typically rely on regular and discrete lag structures, limiting their applicability to regularly sampled data. However, many real-world tasks require dealing with irregularly sampled streams of events, such as sensor streams, healthcare data, and financial transactions. In this work, we propose an extension […]
Decoupling Inference from State Updates in Low-Latency Feature Engines via Probabilistic Thinning
Streaming data systems increasingly underpin Machine Learning workflows that maintain large numbers of continuously updated aggregations. In production settings, each incoming event typically triggers read-modify-write operations to persistent storage, making high-frequency state updates a dominant source of latency, contention, and operational cost. In this work, we decouple inference from state persistence in streaming Machine Learning […]
The Balance between Nuance and Clarity: Decluttering Tabular Sequential Graphs to Counter Money Laundering
Money laundering is not only about moving illicit funds, but about hiding the money’s origin and traces to complicate detection. Financial criminals resort to many methods to avoid regulators and legal thresholds. But analysts investigating alerts, dedicated to pin mule accounts and track suspicious transactions daily, also have theirs. Network visualizations can be key in […]
Uncertainty-Aware Systems for Human-AI Collaboration
Learning to defer (L2D) algorithms improve human-AI collaboration (HAIC) by deferring decisions to human experts when they are more likely to be correct than the AI model. This framework hinges on machine learning (ML) models’ ability to assess their own certainty and that of human experts. L2D struggles in dynamic environments, where distribution shifts impair […]
Responsible AI & The TRUST Framework
Why bother with Responsible AI? What are the tradeoffs? How to get started with Responsible AI? What is the TRUST Framework? In this keynote Pedro presents some context and some misconceptions about Responsible AI and shows how the TRUST Framework can guide the development of Responsible AI systems. Keynote at the Center for Responsible AI Forum 2025
3 áreas de investigación. 1 misión.
Los investigadores de Feedzai están obsesionados con ofrecer la tecnología más reciente para proteger las finanzas a la velocidad de la vida actual.
Feedzai llega a las 100 patentes presentadas
Personas galardonadas
Catarina Belém
Premio Maria de Lourdes Pintasilgo del IST, 2021
Beca Fulbright, 2021
André Cruz
Premio a la mejor tesis de maestría en Ciencias (MSc) en Inteligencia Computacional otorgado por IEEE Portugal, 2020
Sofia Gomes
Finalista de los Portuguese Women In Tech Awards en la categoría de Ingeniera de Sistemas y Redes, 2021
Francisco Silva
Premio a la Excelencia en Academia en la categoría de Ingeniería Eléctrica e Informática otorgado por Ordem dos Engenheiros Sul (OERS), 2026
Sérgio Jesus
Ganador del Vencer o Adamastor por el mejor trabajo por parte de un joven científico en Portugal en Ciencias de la Computación/Ingeniería Eléctrica, por su excelencia y beneficios para la sociedad, 2026
Investigación en acción
Explicaciones de los investigadores que resuelven hoy los problemas del mañana.
Encontrar la verdad: sin más concesiones
IA responsable: identificar y abordar los sesgos de la IA
Latencia en la prevención del fraude: no deje que los números lo engañen
El blog de investigación de Feedzai
Aloja una serie en desarrollo de historias emocionantes y artículos interesantes, que explican los últimos desarrollos sobre cómo nuestros expertos combaten el delito financiero a través de la innovación continua en visualización de datos, investigación de sistemas, ingeniería, ciencia de datos e inteligencia artificial.
Benchmark It Yourself (BIY): Preparing a Dataset and Benchmarking AI Models for Scatterplot-Related Tasks
When we need to visualize and interact with millions, or even just thousands, of individual points while analyzing data, we typically resort to rendering them in the browser using a canvas.
Benchmarking LLMs in Real-World Applications: Pitfalls and Surprises
“Are newer LLMs better?”, In this post, Jean Vieira Alves and Ferran Pla Fernández explore that question with rigorous benchmarking work. Spoiler/hint: recall Betteridge’s law of headlines (“Any headline that ends in a question mark can be answered by the word no.”)
Causal Concept-Based Explanations
Over the years, we have evolved from using simple, often rule-based algorithms to sophisticated machine learning models. These models are incredibly good at finding patterns in large datasets, but due to their complexity it is frequently challenging for a human to understand why a certain input leads to its respective output. This is especially problematic in areas where high-stakes decisions are being made and where human-AI collaboration is critical.
Feedzai TrustScore: Enabling Network Intelligence to Fight Financial Crime
Detecting financial fraud is like finding a moving needle in a shifting haystack. Fraud accounts for a tiny fraction of financial transactions, often less than 0.1%. At the same time, fraudsters are constantly adapting their tactics to evade detection. And this happens within a live and dynamic environment, where financial behaviors and technologies are changing over time. In short, this is an exceptionally difficult problem for financial institutions.
Devolvemos a la comunidad:
código abierto en Feedzai
Retribuimos a la comunidad que hace posible nuestro trabajo. Nuestros paquetes de código abierto son utilizados por científicos de datos e ingenieros de aprendizaje automático (ML) en todo el mundo, y han tenido más de 1M+ downloads.
BIY dataset
A synthetic, annotated dataset (and its generation pipeline) for scatterplot-related tasks.
feedzai-altair-theme
Feedzai’s theme for Altair charts.
OpenL2D
A framework designed to realistically simulate expert decisions on any tabular dataset, enabling Human-AI Collaboration research on public datasets.
SARSum
A comprehensiveness and relevance-aware summarization dataset focusing on the development of Suspicious Activity Reports in the course of Anti Money Laundering Investigations.
Asociaciones académicas
Las asociaciones académicas de Feedzai Research abarcan pasantías, becas, supervisión de doctorado y asociaciones universitarias.
Premios y reconocimiento del trabajo de investigación
World Changing Ideas: finalista de la categoría de software, 2021
Fast Company - World Changing Ideas: finalista de la categoría de IA y datos, 2021
Premios Fintech Breakthrough - Innovación del año en prevención del fraude, 2021
Premios Asia Fintech - Tecnología regulatoria del año, 2021
The Stack - Tech for Good, 2021
Página impresa el 18 de septiembre de 2026. Visite https://www.feedzai.com/es/research/ para consultar la última versión.
