Fraud Networks

In this episode we talk with Bavo DC Campo, a data scientist and statistician, who shares his expertise on the intersection of actuarial science, fraud detection, and social network analytics.

Together we will learn how to use graphs to fight against insurance fraud by uncovering hidden connections between fraudulent claims and bad actors.

Key insights include how social network analytics can detect fraud rings by mapping relationships between policyholders, claims, and service providers, and how the BiRank algorithm, inspired by Google’s PageRank, helps rank suspicious claims based on network structure.

Bavo will also present his iFraud simulator that can be used to model fraudulent networks for detection training purposes.

Do you have a question about fraud detection? Bavo says he will gladly help. Feel free to contact him.

Guest

Bavo DC Campo: I am a data scientist and a statistician, who tries to combine the best of two worlds. I have over 10 years of experience and my area of expertise lies in the construction and validation of predictive models. I also have experience in other research areas, such as clustering and assessing the agreement or reliability of repeated measurements. Further, I am proficient in and have a passion for programming (especially in R). I love to immerse myself in new research projects, which require me to solve complex problems and to analyze the data thoroughly. Tackling new, unfamiliar challenges is something I look forward to as it allows me to grow and develop new knowledge and new skills. I did my PhD in Actuarial Science at the KU Leuven, under the supervision of professor dr Katrien Antonio. My research focused on the development and evaluation of predictive modeling techniques within actuarial science. In my research, I assessed the performance of both statistical and machine learning methods. Another part of my research focused on the development of fraud detection models using social network features. Here, I examined both the methodological and practical part. If you want to read my PhD thesis, you can do so by clicking on this link. Before my PhD, I worked as a biostatistian in the International Ovarian Tumor Analysis (IOTA) group and I stayed connected to biomedical research throughout my whole career. In the IOTA group, I was part of an interdisciplinary team of researchers connected to UZ Leuven and KU Leuven. I worked on numerous projects, which provided me with a firm and solid basis in biostatistics. Furthermore, my main research projects focused on the development and validation of clinical prediction models.