DIG (now version 2.8) is an application for the visual data mining of heterogeneous databases based on virtual reality. The purpose is to facilitate the process of understanding the underlying structure of single or compound databases of a general kind. The method is based on parameterized mappings between the heterogeneous space representing the original data and the virtual reality space.

The mappings can also be constructed for unions of information systems (e.g. heterogeneous and incomplete data sets together with knowledge bases composed by decision rules), simplifying the process of discovery of interesting patterns as well as relationships between the original data and the symbolic expressions representing the structured knowledge.

DIG may be used in: banking, for easy visual tracking of customer accounts to discover business difficulties or aberrations that may lead to loan failures; auditing for accounting irregularities; criminal or behavioural science for tendencies and patterns; astronomy, geology or genomics (see Publications); predictive maintenance (various applications addressed by Monica) predictive health (DIG is part of MonicaMD). In fact DIG can be applied to any ODBC compliant database for knowledge, trend and pattern discovery.

The advantages of a virtual reality environment from the point of view of navigation, data interaction, etc., creates an intuitively simple, and at the same time powerful way to understand and interpret complex data. We will have a full featured multi-platform beta version of DIG available shortly.

Please see examples of DIG at work.