Authors: Phong H. Nguyen, Rafael Henkin, Siming Chen, Natalia Andrienko, Gennady Andrienko, Olivier Thonnard, Cagatay Turkay
Abstract: User behaviour analytics (UBA) systems offer sophisticated models that capture users' behaviour over time with an aim to identify fraudulent activities that do not match with their profile. Making decisions based on such systems; however, requires an in-depth understanding of user behaviour. Motivated by this problem, we present a visual analytics approach to help analysts gain a comprehensive, multi-faceted understanding of user behaviour. As a multidisciplinary team of cyber-security experts and visualisation researchers, we take a user-centred approach to design a visual analytics framework supporting the analysis of collections of users, their organisations and the numerous sessions of activities they conduct on digital applications. The framework is centred around the concept of interactive visual user profiles, where the profiles are built based on features derived from user sessions and visualised with task-informed designs to facilitate interactive exploration and investigation. We externalise a series of analyst goals and tasks, and evaluate our methods through a number of use cases that demonstrate how these tasks are addressed. We observe that with the aid of interactive visual interfaces, analysts are able to conduct exploratory and investigative analysis effectively, and able to unravel the intricacies of user behaviour to make decisions effectively in the evaluation of suspicious users and activities.