KVMap: Business Intelligence & New Visual Analytics

KVMap: Business Intelligence & New Visual Analytics
1 Star2 Stars3 Stars4 Stars5 Stars (No Ratings Yet)

“The increasing power of computer, simulation and sensor technology allows us to produce and store data at ever growing rates. Nevertheless, in virtually every application area, data has no value in itself: In very large amounts, data actually hides the important information and makes information more and more difficult to acquire. Decision makers, analysts, and engineers are often confronted with vast amounts of complex, seemingly inconsistent or incomplete data, which is derived from a number of heterogeneous sources. The goal of analyses is transparent knowledge, which can be applied in the context of future decisions. Visual Analytics is a new interdisciplinary field of information visualization that builds a bridge between the advantages of both human and computer to provide solutions for information overload.

In most Visual Analytics application scenarios, the development of efficient tools to process those large amounts of data is a major challenge. For an interactive visual analysis it is necessary to provide an immediate response to any query. One objective of this project is to develop a system that is capable of processing such data amounts. We are currently developing a database and visualization architecture that utilizes our Visual Analytics cluster and serves as the fundament for all further developments. The main application areas of the technology are finance and insurance, bio-technology, IT security, emergency management and others.

The prototype KVMap shows the possibilities of analysis of complex data sets supported by new visualisation techniques. Statistic correlations between the data are processed and presented in a way that allows the analysts to recognise possible data relationships as patterns. This provides the chance to draw conclusions from hidden correlations in the data gathered from very heterogeneous sources without any prior knowledge. These correlations can be a valuable source for a more detailed analysis and hypothesis creation process.

For finance, insurance and economics, Fraunhofer IGD is developing systems for analysis and presentation of complex, time-dependent and heterogeneous financial and economic data. Visual analytics approaches can be applied to various fields of the financial business: i.e. financial market analysis, risk management, consumer profile analysis, market segmentation, etc. With the help of the new presentation techniques, results such as product analysis, projections and business plans can be displayed in an easier-to-understand form to customers, business partners, and higher management. Moreover, the results can be transferred in real-time to mobile devices (e.g. smartphones and PDAs).

The current prototypes that can be used for the analysis of financial data have been presented at the workshop “Graphical Insights into Financial Data” where they have received a very positive resonance. The prototype FinMotion supports the analysis of correlations of market indicators in a dynamic environment. The system uses animation of data points in a scatterplot to better present development of market variables. Special features of scatterplot glyphs are used to encode more variables in a single view. The data analysis is facilitated also by showing detailed information on demand and by additional functions like zooming, selecting, and highlighting.

The research and application of Visual Analytics technology have been topics of several workshops co-organized by the Fraunhofer IGD:

  • Workshop on Visual Analytics in June 2005
  • Workshop “Visual Analytics – Opportunities for the Financial Industry” in December 2005
  • EU Workshop on Visual Analytics in January 2007.
  • Analytics Day 2007

The recent workshop on “Graphical Insights into Financial Data” in January 2007 has discussed the current trends in visual data analysis for financial institutions. We are closely collaborating with the Computer Science Institute of the University of Konstanz (Prof. Daniel Keim) and other national and international experts in this field. Jörn Kohlhammer, together with David Ebert, Purdue University, and Daniel Keim, is guest editor of the Computers & Graphics Special Issue on Visual Analytics, which will be published by Elsevier in June 2007.”

Link & contacts: