Feedzai Research

State-of-the-Art Innovations to Prevent Financial Crime

Feedzai understands that you can’t fight tomorrow’s fraud and financial crime with today’s solutions. Our dedicated team of scientists, engineers, and technical experts push the limits of known technology to develop advanced AI and engineering solutions that safeguard frictionless financial transactions and protect organizations and individuals from financial crime.

Discover Our Research Specialities

Feedzai Research encompasses Machine Learning, Systems Research, FATE, and Data Visualization. Each group is rigorous in its pursuit of continuous improvement. They perform careful, data-driven experiments to uncover and validate new methodologies and algorithms.

Machine Learning

We develop advanced state-of-the-art machine learning techniques to improve fraud and financial crime detection and prevention.

Feedzai Research disrupts the machine learning workflow to develop innovative solutions that automate and assist the processes of sampling, feature engineering, labeling and annotation, training, and offline and online evaluation, among others.

Research Focus: recurrent neural networks, active learning, transfer learning, graph representation learning, Graph Neural Networks, Bayesian inference, and optimization.


System Research

Systems Research reduces hardware and software costs and time-to-market by improving the platform’s training time and production time needs by focusing on system characteristics such as memory usage, storage usage, throughput, latency, scalability, reliability, and more.

Research Focus: distributed stream processing systems optimize low latency, high throughput, recoverability, checkpointing, scalability, memory consumption, state management, benchmarking, and more.


Fairness + Accountability + Transparency + Ethics (FATE)

The FATE team stands at the forefront of Responsible AI.  In collaboration with top universities and other AI leaders, FATE is on a mission to raise awareness about the importance and impact of ethical AI on society. They develop new approaches to detect, isolate, and mitigate bias in data sets, machine learning models, and AI systems through empirical research.

Research Focus: improve explainability and interpretability of machine learning; enable traceability and governance of the machine learning workflow, explain a model’s impact on fairness and transparency, and enhance ethical and compliant practices.


Data Visualization

The Data Visualization group focuses on creating intuitive, user-centered visualization interfaces and tools to help users see, understand, and reason about their data. They aim to help Fraud Analysts solve the challenges they face while investigating financial crime, and they create tools to help Data Scientists analyze datasets and build models.

Research Focus: bias & fairness visualization, model evaluation, temporal & geospatial visualization.

News

Paper “Promoting Fairness through Hyperparameter Optimization” presented at ICLR 2021 Workshop on Responsible AI (RAI)

Paper “Weakly Supervised Multi-task Learning for Concept-based Explainability” presented at ICLR 2021 Workshop on Weakly Supervised Learning (WeaSul)

Paper “How can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanations” presented at FAccT 2021, the ACM Conference on Fairness, Accountability, and Transparency

Pedro Saleiro gives tutorial “Dealing with bias and fairness in AI systems” at AAAI 2021 together with Rayid Ghani (CMU) and Kit Rodolfa (CMU)

Feedzai Research got two papers, both on innovations in explainability, accepted at the NeurIPS 2020 workshop on Human And Machine in-the-Loop Evaluation and Learning Strategies.

Paper “Machine learning methods to detect money laundering in the Bitcoin blockchain in the presence of label scarcity” accepted for presentation at the KDD Workshop on ML in Finance and accepted for publication at the ICAIF 2020.

“Interleaved Sequence RNNs for Fraud Detection” paper accepted at KDD 2020.

“Dealing with Bias and Fairness in Data Science Systems: A Practical Hands-on Tutorial” accepted at KDD 2020.

Fortune interviews Pedro Bizarro on the effects of coronavirus crisis on cybercriminal behavior.

Project CAMELOT, in partnership with CMU, IST, ULisboa, UCoimbra.

Opinion article about AI and Regulation (Portuguese).

Congressional testimony on “Equitable Algorithms: Examining Ways to Reduce AI Bias in Financial Services” based on joint work with Pedro Saleiro.

Pedro Saleiro interview about what to expect in this decade for AI (Portuguese).

Feedzai co-organizes Lisbon NeurIPS meetup.

Feedzai joins Instituto Superior Técnico Partner Network. Professor Mário Figueiredo is now Feedzai Professor in Machine Learning.

Latest Publications

“Weakly Supervised Multi-task Learning for Concept-based Explainability” https://arxiv.org/abs/2104.12459

“Promoting Fairness through Hyperparameter Optimization” https://arxiv.org/abs/2103.12715

How can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanations, https://arxiv.org/abs/2101.08758

GuiltyWalker: Distance to illicit nodes in the Bitcoin network, https://arxiv.org/abs/2102.05373

TimeSHAP: Explaining Recurrent Models through Sequence Perturbations, https://arxiv.org/abs/2012.00073

Teaching the Machine to Explain Itself using Domain Knowledge, https://arxiv.org/abs/2012.01932

A Bandit-Based Algorithm for Fairness-Aware Hyperparameter Optimization, https://arxiv.org/abs/2010.03665

Machine learning methods to detect money laundering in the Bitcoin blockchain in the presence of label scarcity. arXiv preprint arXiv:2005.14635

Interleaved Sequence RNNs for Fraud Detection. arXiv preprint arXiv:2002.05988 and video

ARMS: Automated rules management system for fraud detection. arXiv preprint arXiv:2002.06075

Automatic Model Monitoring for Data Streams. arXiv preprint arXiv:1908.04240

Automatic detection of points of compromise. U.S. Patent Application No. 16/355,562

Computer memory management during real-time fraudulent transaction analysis. U.S. Patent Application No. 16/102,570

Careers

Help us build the future of fighting fraud with AI

View Open Roles