New DFG project: detect complex insurance fraud with deep learning
20 January 2021, by Andrea Bükow
Photo: HCHE
Together with Prof. Evgeny Burnaev (Skolkovo Institute of Science and Technology, Russia), HCHE core member Prof. Martin Spindler will further develop deep learning architectures to use network structures or graphs as future input. This should enable the automatic detection of fraudulent networks in the insurance sector, for example between doctors and pharmacies. The project titled "Mathematical methods and algorithms for learning-effective embeddings of semi-structured information for anomaly detection problems" is set until 2024 and is funded by both the German and the Russian research community.
