RESUMO
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.
RESUMO
Animated scatterplot visualizations promise to be useful tools for analyzing trends in time-oriented data. We evaluated such a visualization for the analysis of time-oriented medical data. We found 10 medical professionals to test the software which visualizes clinical diabetes patient cohorts. To analyze the usability of the software, the methods "Thinking Aloud" and structured interviews were used. Results show that animated scatterplots do support medical professionals in their daily work, in contrast to more negative results of scientific research in the past.
