Systems Research

The Systems Research group focuses mostly on the performance and reliability of engineering systems. It focuses on projects that enable new software capabilities important for a RiskOps Platform, and improve systems characteristics such as memory, storage, computation, latency, throughput, availability, cloud cost, reliability and stability, etc.

Research Focus:

  • Streaming Engines
  • Graph-based storages
  • ML infrastructure
  • Distributed processing

Recent Publications

RIFF: Inducing Rules for Fraud Detection from Decision Trees

João Lucas Martins, João Bravo, Ana Sofia Gomes, Carlos Soares, Pedro Bizarro

Published at RuleML+RR 2024

arXiv | YouTube

Lightweight Automated Feature Monitoring for Data Streams

João Conde, Ricardo Moreira, João Torres, Pedro Cardoso, Hugo Ferreira, Marco O. P. Sampaio, João Tiago Ascensão, Pedro Bizarro

Published at KDD 2022 - AutoML workshop

PDF | arXiv

Railgun: managing large streaming windows under MAD requirements

Ana Sofia Gomes, João Oliveirinha, Pedro Cardoso, Pedro Bizarro

Published at VLDB 2021 conference

PDF | arXiv | VLDB proceedings | Feedzai Techblog | bibtex | YouTube

Interleaved Sequence RNNs for Fraud Detection

Bernardo Branco, Pedro Abreu, Ana Sofia Gomes, Mariana S.C. Almeida, João Tiago Ascensão, Pedro Bizarro

Published at KDD 2020 conference

PDF | arXiv | bibtex | Feedzai Techblog | YouTube

View all Publications

Related Blog Posts

View all Posts

Empowering Fast Graph Visualizations for Fraud Detection (or Why We Built Our Own Graph Database)

Learn how we boosted Genome, a financial crime visualizer using link analysis, performance up to 100x, by building our graph database.

Francisco Santos and Sofia Gomes

Railgun: A new weapon for mission critical streaming tasks

We present Railgun, a streaming engine that provides accurate metrics with millisecond-level latencies in a distributed setting.

Sofia Gomes

Are Streaming Engines lying to you too?

Streaming engines claim they support sliding windows. In truth what they really have are stepping windows. Have you been lied to as well?

Pedro Cardoso

Empowering Fast Graph Visualizations for Fraud Detection (or Why We Built Our Own Graph Database)

Learn how we boosted Genome, a financial crime visualizer using link analysis, performance up to 100x, by building our graph database.

Francisco Santos and Sofia Gomes

Railgun: A new weapon for mission critical streaming tasks

We present Railgun, a streaming engine that provides accurate metrics with millisecond-level latencies in a distributed setting.

Sofia Gomes

Are Streaming Engines lying to you too?

Streaming engines claim they support sliding windows. In truth what they really have are stepping windows. Have you been lied to as well?

Pedro Cardoso

Page printed in 21 Nov 2024. Plase see https://research.feedzai.com/research_area/systems-research for the latest version.