Research Blog

Welcome to Feedzai Research Blog, where we feature an ongoing series of exciting tales and cool articles, elucidating the latest developments on how our experts combat villainous villains through continuous innovation in data visualization, system research, engineering, data science and Artificial Intelligence.

TimeSHAP: Explaining recurrent models through sequence perturbations

Recurrent Neural Networks (RNNs) are a family of models used for sequential tasks, such as predicting financial fraud based on customer behavior. These models are very powerful, but their decision processes are opaque and unintelligible to humans and rendering them black boxes to humans. Understanding how RNNs work is imperative to assess whether the model is relying on any spurious correlations or discriminating against certain groups. In this blog post, we provide an overview of TimeSHAP, a novel model-agnostic recurrent explainer developed at Feedzai. TimeSHAP extends the KernelSHAP explainer to recurrent models. You can try TimeSHAP at Feedzai’s Github.

Joao Bento, André Cruz, Pedro Saleiro

Understanding FairGBM: Feedzai’s Experts Discuss the Breakthrough

Feedzai recently announced that we are making our groundbreaking FairGBM algorithm available via open source. In this vlog, experts from Feedzai’s Research team discuss the algorithm’s importance, why it represents a significant breakthrough in machine learning fairness beyond financial services, and why we decided to release it via open source.

Pedro Saleiro

Analyzing Data Drift: How We Designed Visualizations to Support Feature Investigation

Find more about how we designed visualizations to support our new tool to automatically detect drift in data over time, Feature Investigation.

João Palmeiro

Feature Investigation: Automatically Detect Drift in your Data Over Time

Find out more about Feature Investigation, a new tool to automatically detect drift in your data over time

Ricardo Moreira, Marco Sampaio, Hugo Ferreira

Building Feedzai’s First Figma Charting Library: A Summer Experience

Find out more about the recent Figma Library of charts created to help Feedzai’s Data Visualization and UX teams in their mockups creation process.

Francisca Calisto

Styling Altair Charts with the feedzai-altair-theme

Find out about Altair themes and a new Python package for Data Visualization with Altair.

João Palmeiro

How Feedzai ARMS automates rule management in large scale systems

Learn how Feedzai ARMS automatically optimizes rule systems, all while achieving the detection performance required by our clients.

Ricardo Barata and Hugo Ferreira

Why Responsible AI Should be Table Stakes in Financial Services

As artificial intelligence (AI) becomes increasingly used in financial services, it’s essential that financial institutions (FIs) trust the technology to work as intended and that it aligns with their ethical values. Implementing Responsible AI principles is not only the most effective way FIs can protect their customers and their brand from misbehaving AI - it’s also the right thing to do.

Pedro Saleiro

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

Light Speedy Profiling to Fight Fraud

An overview of profiling methods, with data science and engineering experiments using exponential moving averages.

Pedro Cardoso and Marco O. P. Sampaio

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

Understanding AI Bias in Banking

As banks invest in artificial intelligence (AI) solutions to improve their services they must understand how AI bias can influence their operations, public perceptions, and their customers’ lives. Follow the blog for the latest trends in ethical AI and delve into other posts on this.

Pedro Saleiro

ML-Powered Automatic Model Monitoring

The life of a data scientist at Feedzai, deploying and maintaining machine learning (ML) models in large scale production environments, constantly offers new exciting and challenging problems. In this post, we will discuss

Marco O. P. Sampaio

Casting Deep Learning Nets on Financial Crime

Can deep learning improve fraud detection models? Read about our exploration into recurrent neural networks and how they can be used to help prevent financial crime.

Pedro Abreu

Connecting the dots: how to see the shape of fraud

At Feedzai, we’re in a constant and ever-evolving fight against financial crime. To be efficient fraud fighters, we leverage large amounts of data. Data scientists use our platform to build machine learning models from historical data, which are then deployed to stop worldwide fraudsters in real time.

Beatriz Malveiro

Page printed in 31 Jan 2023. Plase see https://research.feedzai.com/research-blog for the latest version.