This project develops a hybrid fraud detection model by combining graph-based learning and time-series analysis to capture complex transaction relationships, aiming to enhance fraud prediction accuracy while minimizing false positives in large-scale payment datasets.
The Junior Conference on DataScience and Engeneering 2022 (JDSE) took place on september 15-16, on the Polytechnique campus (Palaiseau).
Hugo Thimonier has the opportunity to present “TracInAD: Measuring Influence for Anomaly Detection” to the audience.
Marc Velay won the best poster contest with his poster about “Robustness Analysis of Deep RL for Portfolio Selection”.
Hopular applied to Fraud Detection.
Constructing probabilistic rule list.
Constructing probabilistic rule list.
An investigation about the automation of playlists building for a music provider.
An investigation about using graph models and deep learning.
Template by Bootstrapious. Ported to Hugo by DevCows.
