Supervisor: prof. David Martens
Co-supervisor: prof. Bruno Peeters

Summary of the project: Automated data mining systems that look for fraud patterns in historical data, have been on the rise to tackle the important issue of tax fraud. In this multidisciplinary project, we will develop, apply and validate new data mining techniques to accurately predict which entities (be it companies or persons) are likely fraudsters, by considering concepts as different data types, privacy, intuitiveness and comprehensibility of the predictions. This proposal will make use of existing contacts with the federal government, and will be the formal start of a novel research theme within the Antwerp Tax Academy.

Publications: Data Mining for Fraud Detection using Invoicing Data: A Case Study in Fiscal Residence Fraud

• UNIGE: PhD position on Machine Learning for representation learning
• Idiap/EPFL: PhD and Internship Positions in Social Computing
• NYU Data Science Program – Things to Know