You are here

Adaptive real-time machine learning for credit card fraud detection


  • Gianluca Bontempi (project coordinator and Phd supervisor) Professor at MLG - Computer Science Department, ULB
  • Olivier Caelen (collaborator and industrial supervisor) Atos Worldline fraud detection team, Phd Computer Science Department, ULB
  • Andrea Dal Pozzolo (researcher) Phd candidate at MLG - Computer Science Department, ULB

Funding: Doctiris, Innoviris, Brussels Region

Duration: 2012-2014, renewable for other two more years.

Project Overview:

Nowadays, enterprises and public institutions have to face a growing presence of frauds and consequently need automatic systems able to support fraud detection and fight. 

These systems are essential since it is not always possible or easy for a human analyst to detect fraudulent patterns in transaction datasets, often characterized by a large number of samples, many dimensions and online update.

Project Objectives:

Design, assess and validate a machine learning frame- work able to calibrate in a automatic, real-time and adaptive manner the ATOS Worldline fraud detection strategy.

The goal is to provide the industrial partner with a set of learning tools to be integrated within the credit card fraud detection process daily run by ATOS Worldline in order to improve its robustness, performance and accuracy. 


Theme by Danetsoft and Danang Probo Sayekti inspired by Maksimer