Videos
Playlists
Animated Product Videos
5 Videos • Playlist
Anti-Money Laundering
8 Videos • Playlist
Awards & Recognition
2 Videos • Playlist
Latest
14:59
Weakly Supervised Multitask Learning for Concept-based Explainability
This work addresses two main limitations to the implementation of concept-based explainability in practice: concept labels’ scarcity and the joint […]
23:17
Teaching the Machine to Explain Itself using Domain Knowledge
We propose JOEL, a neural network-based framework that jointly learns a decision task (e.g., fraud detection), and associated domain knowledge […]
23:05
Promoting Fairness through Hyperparameter Optimization
In this work, we mitigate the risk of building ML models that discriminate by applying a simple and easily deployable […]
23:26
How can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanations
An evaluation framework for explainable AI methods focused on how explanations impact human decision-maker’s efficiency. Authors: Sérgio Jesus, Catarina Belém, […]
19:45
TimeSHAP: Explaining Recurrent Models through Sequence Perturbations
TimeSHAP is a post-hoc, model-agnostic, recurrent explainer that calculates the most important events and features throughout a sequence. TimeSHAP also […]
04:44
Interleaved Sequence RNNs for Fraud Detection
Interleaved Sequence RNNs for Fraud Detection Authors: Bernardo Branco, Pedro Abreu, Ana Sofia Gomes, Mariana S. C. Almeida, João Tiago […]
02:57
Interleaved Sequence RNNs for Fraud Detection (KDD’2020 Promotional Video)
Interleaved Sequence RNNs for Fraud Detection Authors: Bernardo Branco, Pedro Abreu, Ana Sofia Gomes, Mariana S. C. Almeida, João Tiago […]
09:58
Railgun: Managing Large Streaming Windows Under MAD Requirements
Some mission-critical systems, e.g., fraud detection, require accurate, real-time metrics over long-time sliding windows on applications that demand high throughput […]
15:01
GuiltyWalker: Distance to Illicit Nodes in the Bitcoin Network
Money laundering is a global phenomenon with wide-reaching social and economic consequences. Cryptocurrencies are particularly susceptible due to the lack […]
03:28
Active Learning for Online Training in Imbalanced Data Streams Under Cold Start
Labeled data is essential in modern systems that rely on Machine Learning (ML) for predictive modeling. Such systems may suffer […]
15:03
Finding Nemo: Fishing in Banking Networks Using Network Motifs
Banking fraud causes billion-dollar losses for banks worldwide. In fraud detection, graphs help understand complex transaction patterns and discover new […]
04:01
GUDIE: A Flexible, User-defined Method to Extract Subgraphs of Interest from Large Graphs
Large, dense, small-world networks often emerge from social phenomena, including financial networks, social media, or epidemiology. As networks grow in […]
Page printed in May 9, 2025. Plase see https://www.feedzai.com/insights/videos/page/5 for the latest version.