No abstract

Financial institutions are interested in ensuring security and quality for their customers. Banks, for instance, need to identify and stop harmful transactions in a timely manner. In order to detect fraudulent operations, data mining techniques and customer profile analysis are commonly used. However, these approaches are not supported by Visual Analytics techniques yet. Visual Analytics techniques have potential to considerably enhance the knowledge discovery process and increase the detection and prediction accuracy of financial fraud detection systems. Thus, we propose EVA, a Visual Analytics approach for supporting fraud investigation, fine-tuning fraud detection algorithms, and thus, reducing false positive alarms.

No abstract

Contemporary video games are highly complex systems with many interacting variables. To make sure that a game provides a satisfying experience, a meaningful analysis of gameplay data is crucial, particularly because the quality of a game directly relates to the experience a user gains from playing it. Automatic instrumentation techniques are increasingly used to record data during playtests. However, the evaluation of the data requires strong analytical skills and experience. The visualization of such gameplay data is essentially an information visualization problem, where a large number of variables have to be displayed in a comprehensible way in order to be able to make global judgments. This paper presents a visualization tool to assist the analytical process. It visualizes the game space as a set of nodes which players visit over the course of a game and is also suitable to observe timedependent information, such as player distribution. Our tool is not tailored to a specific type of genre. To show the flexibility of our approach we use two different kinds of games as case studies.

No abstract