Raphaël Minato
Transformer-based robust predictive models for financial temporal series with concept drift.
CIKM 2026
Two papers from the Lusis chair will be presented at CIKM 2026 in Rome: kernel-based anomaly detection and knowledge-informed causal discovery.
Fraud Campaign Detection and Rule Learning for Card Payments
Investigate whether transaction groups and interpretable rules, including rules proposed by language models, improve future fraud detection beyond a LightGBM baseline.
Relational steering for tabular anomaly detection
Investigating whether context-dependent interventions in tabular models reveal anomalies that violate relationships between variables.
MICCAI 2026 — MultiTab Best Paper Award
Our paper on cross-modal anomaly screening with tabular foundation models received the Best Paper Award at the MultiTab workshop, held on September 27, 2026 in Strasbourg during MICCAI 2026.
Flow Matching for Credit Card Fraud Detection
Evaluate one-step flow matching for credit card fraud detection, comparing classification quality, training cost and inference speed with gradient boosted trees.
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
Enhancing Trading Strategy Robustness through Anomaly Detection
This project explores the use of anomaly detection techniques, such as One-Class SVM, to identify the conditions under which algorithmic trading strategies are likely to succeed, ensuring their applicability and extending the approach to portfolio-wide strategy optimization.