An architecture for the SPIN! spatial data mining platform

Geographic Information Systems (GIS) are widely used for analysing and visualizing georeferenced data. In the last few years, a new generation of Geographic Information Systems has emerged that extends the interactivity of dynamically generated maps, greatly enhancing visual exploratory data analysis ([1], [3], [6], [13]). While being an exciting development for automating cartography, these systems have limited capabilities to visualize attribute interaction on a map having more than a few dimensions. Hence, complex multi-variate dependencies are easily overlooked.