Software

Bayesia announces the release of the version 4.2 of BayesiaLab, the leading software in the market of Bayesian networks and Data Mining.

The main new features of this release are:

• Markov Blanket export in SAS macro. In order to ease the deployment of the Bayesian scoring functions, in direct marketing applications for example, this tool allows to export the Markov blanket of the target variable in a SAS macro. This macro can then perform exact inference on the target variable from the values of the Markov blanket's nodes.

• Variable Clustering. This algorithm uses the graph structure of the Bayesian network and the forces of its arcs to cluster the variables that are close semantically;

• Multiple Clustering. Allows to carry out data clustering on the classes of variables returned by the variable clustering algorithm. A latent variable synthesizing the manifest variables is induced for each class. It is then possible to discover the probabilistic relations that hold between these latent variables, and, possibly, with the manifest variables;

• Data Clustering. The implementation of a new score and the development of a new search strategy allow obtaining much more relevant clusters. These clusters are more stable, and come with an improved purity;

• Mapping tool allowing to have a graphical representation of the clusters;

• Batch Joint Probability. In order to detect outliers by taking into account all the variables this tool allows to compute the joint probability of each record of a database;
• and, as usual, increased ergonomics of the interface and performance improvements.

You can consult the newsletter that describes more in details the new functionalities of BayesiaLab 4.2, download BayesiaLab 4.2 for a new 30 days evaluation period, and you can also have a look at the dynamic and static presentations that illustrate successful applications of BayesiaLab.