Code
Feedzai Research open-source contributions, packages, and projects
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.
Aequitas
A bias auditing and Fair ML toolkit for data scientists, machine learning researchers, and policymakers. Aequitas was started by the Data Science for Social Good Foundation.
FairGBM
An easy-to-use and lightweight fairness-aware ML algorithm with state-of-the-art performance on tabular datasets.
TimeSHAP
A model-agnostic, recurrent explainer that builds upon KernelSHAP and extends it to the sequential domain.
BAF
A suite of datasets (published at NeurIPS 2022) with 6 synthetic bank account fraud tabular datasets, to evaluate ML and fair ML
Page printed in 29 Dec 2025. Plase see https://research.feedzai.com/code for the latest version.