Fraud detection
Today, electronic payments by credit card have become widespread on the planet thanks to the Internet. These payments represent an ever-increasing volume of more than US$500 billion annually, and fraud accounts for less than 0.5% of the number of these transactions. Globally, this represents an estimated US$25 billion in losses per year and this loss is increasing.
Irrespective of the amount of this fraud, all possible detection measures must of course be implemented to limit its spread. This is why a great deal of research has been carried out on this problem over the last 20 years.
As the publisher of a high-performance transactional platform for payment systems, LUSIS is therefore primarily interested in fraud countermeasures. Within the framework of the LUSIS chair, we wish to study fraud detection both from the point of view of algorithm performance, but also with a constraint of realism of implementation and this on real data.
From a technical point of view, the difficulties and locks are at different levels :
- very unbalanced data sets, there are less than 0.5% of fraudulent transactions,
- need to avoid false positives at all costs,
- emergence of new fraud strategies,
- online detection more difficult than offline,
- changes in customers’ consumption habits (concept drift),
- need to explain the refusal of a transaction
ICLR 2025
José-Lucas De Melo Costa, Bich-Liên Doan and Fabrice Popineau will attend ICLR2025 in Singapour to present T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data Hugo Thimonier, who is now at Emobot, will be there too.
ILB 2025
José-Lucas De Melo Costa, Fabrice Daniel and Fabrice Popineau are presenting Comparative Evaluation of Anomaly Detection Methods for Fraud Detection in Online Credit Card Payments at the 18th Financial Risks International Forum in Paris organized by Institut Louis Bachelier.
More about the event:
Day 1 kick off Day 1 parallel sessions Day 1 wrap-up 2nd day kick off 2nd day parallel sessions
CIKM 2024
Fabrice Popineau is at CIKM2024 in Boise, Idaho to present Retrieval Augmented Deep Anomaly Detection for tabular Data.
Stream graphs for fraud detection
Stream graphs applied to fraud detection.
Hugo Thimonier PhD thesis defense
The thesis is in the Machine Learning domain and its title is “Advancing Anomaly Detection in Tabular Data: A Case-Study on Credit Card Fraud Identification”, under the supervision of Bich-Liên DOAN, Fabrice POPINEAU and Arpad RIMMEL.
The defense will happen on Monday, September 30th at 14:00 in the room 435 of the LISN laboratory. The defense will be in English. For those who cannot attend in person, there will be a visio-conference whose link will be found at https://popineau.pages.centralesupelec.fr/soutenance-hugo-thimonier/ .
ICML 2024
Hugo Thimonier is at ICML2024 to present Beyond Individual Input for Deep Anomaly Detection on Tabular Data
2024 Workshop on Anomaly Detection
Workshop on Anomaly Detection
We’re pleased to invite you to take part in the symposium on anomaly detection to be held on February 29 at CentraleSupélec. It’s also an opportunity for your teams' researchers/doctoral students to present their research work on the subject, either in the form of a 10-minute oral presentation, or a poster. Please send your intention to participate to chaire-lusis@centralesupelec.fr by 15th February 2024.
Subject: Symposium on anomaly detection
NeurIPS 2023
Hugo Thimonier and Bich-Liên Doan are at NeurIPS2023 for the Table Representation Learning Workshop