no code implementations • 11 Mar 2024 • Jean V. Alves, Diogo Leitão, Sérgio Jesus, Marco O. P. Sampaio, Javier Liébana, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro
Learning to defer (L2D) aims to improve human-AI collaboration systems by learning how to defer decisions to humans when they are more likely to be correct than an ML classifier.
no code implementations • 16 Jan 2024 • Ricardo Moreira, Jacopo Bono, Mário Cardoso, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro
Lastly, explanation methods should be efficient and not compromise the performance of the predictive task.
1 code implementation • 20 Dec 2023 • Jean V. Alves, Diogo Leitão, Sérgio Jesus, Marco O. P. Sampaio, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro
Financial fraud detection is a high-stakes setting where algorithms and human experts often work in tandem; however, there are no publicly available datasets for L2D concerning this important application of human-AI teaming.
no code implementations • 28 Jul 2023 • Tiago Leon Melo, João Bravo, Marco O. P. Sampaio, Paolo Romano, Hugo Ferreira, João Tiago Ascensão, Pedro Bizarro
Adversarial attacks are a major concern in security-centered applications, where malicious actors continuously try to mislead Machine Learning (ML) models into wrongly classifying fraudulent activity as legitimate, whereas system maintainers try to stop them.
no code implementations • 25 Jul 2023 • Ricardo Ribeiro Pereira, Jacopo Bono, João Tiago Ascensão, David Aparício, Pedro Ribeiro, Pedro Bizarro
In the former, our method moves cumulative amounts close to 350 thousand dollars through a network of accounts without being detected by an existing system.
no code implementations • 17 Jul 2023 • Ahmad Naser Eddin, Jacopo Bono, David Aparício, Hugo Ferreira, João Ascensão, Pedro Ribeiro, Pedro Bizarro
We demonstrate that our graph-sprints features, combined with a machine learning classifier, achieve competitive performance (outperforming all baselines for the node classification tasks in five datasets).
no code implementations • 29 Mar 2023 • José Pombal, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro
Data valuation is a ML field that studies the value of training instances towards a given predictive task.
2 code implementations • 24 Nov 2022 • Sérgio Jesus, José Pombal, Duarte Alves, André Cruz, Pedro Saleiro, Rita P. Ribeiro, João Gama, Pedro Bizarro
The suite was generated by applying state-of-the-art tabular data generation techniques on an anonymized, real-world bank account opening fraud detection dataset.
no code implementations • 25 Oct 2022 • Mário Cardoso, Pedro Saleiro, Pedro Bizarro
Reviewing these cases is a cumbersome and complex task that requires analysts to navigate a large network of financial interactions to validate suspicious movements.
1 code implementation • 16 Sep 2022 • André F Cruz, Catarina Belém, Sérgio Jesus, João Bravo, Pedro Saleiro, Pedro Bizarro
Tabular data is prevalent in many high-stakes domains, such as financial services or public policy.
no code implementations • 18 Jul 2022 • João Conde, Ricardo Moreira, João Torres, Pedro Cardoso, Hugo R. C. Ferreira, Marco O. P. Sampaio, João Tiago Ascensão, Pedro Bizarro
We propose a flexible system, Feature Monitoring (FM), that detects data drifts in such data sets, with a small and constant memory footprint and a small computational cost in streaming applications.
no code implementations • 13 Jul 2022 • José Pombal, André F. Cruz, João Bravo, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro
The unparalleled ability of machine learning algorithms to learn patterns from data also enables them to incorporate biases embedded within.
no code implementations • 27 Jun 2022 • José Pombal, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro
The unparalleled ability of machine learning algorithms to learn patterns from data also enables them to incorporate biases embedded within.
no code implementations • 27 Jun 2022 • Diogo Leitão, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro
Human-AI collaboration (HAIC) in decision-making aims to create synergistic teaming between human decision-makers and AI systems.
no code implementations • 24 Jun 2022 • Kasun Amarasinghe, Kit T. Rodolfa, Sérgio Jesus, Valerie Chen, Vladimir Balayan, Pedro Saleiro, Pedro Bizarro, Ameet Talwalkar, Rayid Ghani
Most existing evaluations of explainable machine learning (ML) methods rely on simplifying assumptions or proxies that do not reflect real-world use cases; the handful of more robust evaluations on real-world settings have shortcomings in their design, resulting in limited conclusions of methods' real-world utility.
no code implementations • 7 May 2022 • João Bento Sousa, Ricardo Moreira, Vladimir Balayan, Pedro Saleiro, Pedro Bizarro
Concept-based explanations aims to fill the model interpretability gap for non-technical humans-in-the-loop.
no code implementations • 29 Apr 2022 • João Palmeiro, Beatriz Malveiro, Rita Costa, David Polido, Ricardo Moreira, Pedro Bizarro
We propose Data+Shift, a visual analytics tool to support data scientists in the task of investigating the underlying factors of shift in data features in the context of fraud detection.
no code implementations • 14 Dec 2021 • Ahmad Naser Eddin, Jacopo Bono, David Aparício, David Polido, João Tiago Ascensão, Pedro Bizarro, Pedro Ribeiro
Money laundering is a global problem that concerns legitimizing proceeds from serious felonies (1. 7-4 trillion euros annually) such as drug dealing, human trafficking, or corruption.
no code implementations • 16 Jul 2021 • Ricardo Barata, Miguel Leite, Ricardo Pacheco, Marco O. P. Sampaio, João Tiago Ascensão, Pedro Bizarro
Modern systems that rely on Machine Learning (ML) for predictive modelling, may suffer from the cold-start problem: supervised models work well but, initially, there are no labels, which are costly or slow to obtain.
no code implementations • 26 Apr 2021 • Catarina Belém, Vladimir Balayan, Pedro Saleiro, Pedro Bizarro
In ML-aided decision-making tasks, such as fraud detection or medical diagnosis, the human-in-the-loop, usually a domain-expert without technical ML knowledge, prefers high-level concept-based explanations instead of low-level explanations based on model features.
2 code implementations • 23 Mar 2021 • André F. Cruz, Pedro Saleiro, Catarina Belém, Carlos Soares, Pedro Bizarro
Considerable research effort has been guided towards algorithmic fairness but real-world adoption of bias reduction techniques is still scarce.
no code implementations • 10 Feb 2021 • Catarina Oliveira, João Torres, Maria Inês Silva, David Aparício, João Tiago Ascensão, Pedro Bizarro
Money laundering is a global phenomenon with wide-reaching social and economic consequences.
no code implementations • 21 Jan 2021 • Sérgio Jesus, Catarina Belém, Vladimir Balayan, João Bento, Pedro Saleiro, Pedro Bizarro, João Gama
We conducted an experiment following XAI Test to evaluate three popular post-hoc explanation methods -- LIME, SHAP, and TreeInterpreter -- on a real-world fraud detection task, with real data, a deployed ML model, and fraud analysts.
Decision Making Explainable Artificial Intelligence (XAI) +1
1 code implementation • 30 Nov 2020 • João Bento, Pedro Saleiro, André F. Cruz, Mário A. T. Figueiredo, Pedro Bizarro
Although recurrent neural networks (RNNs) are state-of-the-art in numerous sequential decision-making tasks, there has been little research on explaining their predictions.
no code implementations • 27 Nov 2020 • Vladimir Balayan, Pedro Saleiro, Catarina Belém, Ludwig Krippahl, Pedro Bizarro
Moreover, we collect the domain feedback from a pool of certified experts and use it to ameliorate the model (human teaching), hence promoting seamless and better suited explanations.
no code implementations • 7 Oct 2020 • André F. Cruz, Pedro Saleiro, Catarina Belém, Carlos Soares, Pedro Bizarro
Hence, coupled with the lack of tools for ML practitioners, real-world adoption of bias reduction methods is still scarce.
no code implementations • 24 Sep 2020 • Miguel Araujo, Miguel Almeida, Jaime Ferreira, Luis Silva, Pedro Bizarro
Bank transaction fraud results in over $13B annual losses for banks, merchants, and card holders worldwide.
1 code implementation • 29 May 2020 • Joana Lorenz, Maria Inês Silva, David Aparício, João Tiago Ascensão, Pedro Bizarro
First, we show that existing state-of-the-art solutions using unsupervised anomaly detection methods are inadequate to detect the illicit patterns in a real Bitcoin transaction dataset.
no code implementations • 14 Feb 2020 • Bernardo Branco, Pedro Abreu, Ana Sofia Gomes, Mariana S. C. Almeida, João Tiago Ascensão, Pedro Bizarro
Payment card fraud causes multibillion dollar losses for banks and merchants worldwide, often fueling complex criminal activities.
1 code implementation • 14 Feb 2020 • David Aparício, Ricardo Barata, João Bravo, João Tiago Ascensão, Pedro Bizarro
We propose ARMS, an automated rules management system that evaluates the contribution of individual rules and optimizes the set of active rules using heuristic search and a user-defined loss-function.
no code implementations • 12 Aug 2019 • Fábio Pinto, Marco O. P. Sampaio, Pedro Bizarro
We evaluated SAMM using human feedback from domain experts, by sending them 100 reports generated by the system.