Proactive computing requires capabilities for forecasting, real-
time decision-making and visual analytics. These capabilities are
extremely important in a multitude of application domains. E.g.
no system supports fraud forecasting. Furthermore, a typical fraud
detection system may raise up to 9 false alarms for each true
alarm. Without an appropriate explanation of why a specific
transaction is considered fraudulent, the operator overseeing
transactions will not be able to confirm the fraud and will have to
either let it go through, or contact the end user, spending valuable
time. We propose exposing the user to how proactive computing
works through visual analytics.
To summarize, our methodology supports on-the-fly, low-latency
processing of extremely large, geographically distributed, noisy
event streams and historical data, for recognizing and forecasting
opportunities and threats, making decisions to capitalize on the
opportunities and mitigate the threats, and explaining, through
user-interaction, the decisions to human operators in order to
facilitate informed decision execution