Visual Analytics: Definition, Process, and Challenges - Information Visualization: Human-Centered Issues and Perspectives - page 165

statistical and mathematical techniques, such as spatio-temporal data analysis or
link mining depending on the nature of the dataset under study. The process then
enters a loop where the user can gain knowledge on the data, ideally driving the
system toward more focused and more adequate analytical techniques. Dually,
interacting on the visual representation, the user will gain a better understanding
of the visualization itself commanding for different views helping him or her to
go beyond the visual and ultimately confirm hypotheses built from previous
iterations (see Figure 4).
Fig. 4. The sense-making loop for Visual Analytics based on the simple model of
visualization by Wijk [42].
5 Application Challenges
Visual Analytics is a highly application oriented discipline driven by practical
requirements in important domains. Without attempting a complete survey over
all possible application areas, we sketch the potential applicability of Visual
Analytics technology in a few key domains.
In the Engineering domain, Visual Analytics can contribute to speed-up de-
velopment time for products, materials, tools and production methods by offering
more effective, intelligent access to the wealth of complex information resulting
from prototype development, experimental test series, customers' feedback, and
many other performance metrics. One key goal of applied Visual Analytics in
the engineering domain will be the analysis of the complexity of the production
systems in correlation with the achieved output, for an ecient and effective
improvement of the production environments.
Financial Analysis is a prototypical promising application area for Visual
Analytics. Analysts in this domain are confronted with streams of heterogeneous
information from different sources available at high update rates, and of varying