Safarii is a state-of-the-art Data Mining environment for analysing large relational databases. It is unique in its wide support for a new data analysis paradigm, called Multi-Relational Data Mining (MRDM). This makes it an ideal tool for knowledge discovery in a wide range of industries, such as retail, enterprise resource planning, banking, e-commerce, bio-informatics and molecular modelling.

Safarii can be used as a stand-alone Data Mining tool through the easy-to-use graphical user interface. The XML dialect MRML that comes with Safarii can be used to specify the data model of the application's database. As Safarii works directly on the relational database, without requiring extensive pre-processing, it can be easily used by non-expert users such as managers and domain experts. The GUI supports the Safarii methodology which simplifies the analysis of complex multi-relational data, and results can be easily inspected through a range of graphs and tables.

Furthermore, the package offers a high-level API for easy integration in existing vertical applications. We also provide technical support for optimal deployment of the software. Safarii complements the Business Intelligence and Data Mining services of Kiminkii. Along with a range of other data analysis tools, Safarii is used by our consultants to provide complete solutions in a wide variety of domains.

A detailed walkthrough of the features of Safarii 2.0 can be found here.

Safarii comes with an accompanying pre-processing tool, called ProSafarii. This tool provides a number of classes of transformation that can be applied to the relational database at hand. ProSafarii will analyse the structure and content of the database, and suggest a number of useful operations. Although pre-processing is optional when using Safarii, these transformations may often help to optimise the outcome. The different transformations are designed to work well in the domain of Multi-Relational Data Mining. These transformations include operations such as denormalisation, aggregation and multi-relational discretisation. Safarii and ProSafarii are tightly coupled, such that the outcome of the pre-processing stage can be directly mined by Safarii.

For more details and pricing information concerning Safarii and ProSafarii, please contact Starting from version v1.2 we also offer an academic license at highly reduced rates.

Detailed description

As most Data Mining tools, Safarii mines a given database for subgroups with interesting or surprising characteristics (customers with a high response rate to a mailing, website visitors with above-average spending, a class of chemical compounds with increased carcinogenic potential). Whereas traditional tools only deal with a single table and the flat features stored in there (age, balance, etc.), Safarii is able to involve structural information stored in several tables. This enables Safarii not only to deal with objects that are inherently structural (molecules, weblogs, etc.) and hard to process by traditional tools, but also to integrate data originating from multiple sources such as different business applications, as well as information from previous analyses and domain knowledge. Safarii supports a range of techniques for exploratory data analysis, building predictive models, and deploying the results in an operational environment.

New features in version 2.0

The recently released version 2.0 contains a number of new features for improved discovery of multi-relational knowledge, as well as new facilities for building global models out of the local patterns Safarii discovers. Safarii 2.0 contains a number of new algorithms, notably Support Vector Machines, Bayesian Networks and Pattern Teams. Furthermore, a list of bug-fixes and detailed changes suggested by current users have been incorporated. New features of Safarii in detail:

Technical specifications