User Interface

Build Bayesian networks from data and/or expert opinion. Perform advanced queries and analytics.

Bayesian networks

Fast & efficient software for Bayesian networks

Causal models

Networks can be causal, and support interventions. Discrete and/or continuous nodes.

Decision graphs

Automate the decision making process. Also known as influence diagrams.

Dynamic Bayesian networks

Model multi-variate time series and sequences

Evidence optimization

Intelligently search sets of evidence to maximize/minimize a function (based on an expression), a continuous variable, or a discrete state.

Causal Evidence optimization

Intelligently search sets of interventions to maximize/minimize a function (based on an expression), a continuous variable, or a discrete state.

Latent variables

Model hidden patterns / automate feature extraction

Value of Information

Guide diagnostic / troubleshooting applications.

Automated Insight

Automatically extract important information from data

Pattern analysis

Detect and describe import attributes of a target state, such as a cluster in a mixture model.


How unusual/anomalous is your current data? Can your model be trusted?

Fast inference

100x faster than a naive implementation. Over a decade of research.

Data connectivity (API)

Connect to databases, spreadsheets, No-Sql stores and even custom data sources

Retracted analysis

Anomaly detection diagnostics.

Missing data

Missing data natively supported during both learning and prediction, and for both discrete and continuous variables

Log-Likelihood analysis

Analyze the log-likelihood with different evidence subsets

Discrete & continuous variables

Support for both discrete & continuous variable, as well as latent variables for expressing complex distributions

Batch query

Perform queries on entire data sources

Link strength / associations

How strong are the links/relationships in your model?

Impact analysis

How susceptible are your predictions/queries to changes in evidence?

Data connectivity (User Interface)

Connect to many different databases, spreadsheets and No-Sql stores


A robust and efficient pure .NET API for building intelligent applications and services

Java API

A robust and efficient pure Java API for building intelligent applications and services

Cluster analysis

Automatically evaluate more expressive models and hidden patterns using cluster analysis for latent variables

Parameter learning

Learn the parameters of your model from data. Includes support for missing data, discrete, continuous & hybrid networks

Structural learning

Learn the structure (links) in a network. 5 different algorithms

Case weights

Assign a weight to each row (or case). Great for historic data weighting, and learning from data with probabilities attached

Sensitivity to parameters

How sensitive are you queries/predictions to the model parameters?

In-sample anomaly detection

Identify anomalous data within a training data set.

Advanced query calculator

Perform advanced queries/prediction such as P(X,Y[t+3],Y[t+4] | Z)

Noisy nodes

Model nodes with large numbers of parents. Includes support for scalable inference and parameter learning.

Multi-variable nodes

Nodes can contain multiple variables, for powerful modeling

Data (Scenario) explorer

Easily explore scenarios in the User Interface.

Big data

Bayes Server supports Big Data platforms & technologies such as Apache Spark & Hadoop

R integration

The Bayes Server API can be called from R. Our code center contains examples.

Python integration

The Bayes Server API can be called from Python. Our code center contains examples.

Matlab integration

The Bayes Server API can be called from Matlab. Our code center contains examples.

Excel functions

The Bayes Server API can be called from within Excel functions. Our code center contains examples.

Data sampling

Generate data from a model. Help understand/visualize your model, or generate test data.

Online learning (adaptation)

Incrementally update (adapt) your model as new data arives.


Although continuous variables are fully supported, sometimes it can be useful to discretize. 3 discretization algorithms included.

Add nodes from data

Advanced support for creating variables from a wide variety of data sources.

Retract evidence

Predict a variable as if it did not have evidence set on it. Great for prediction and anomaly detection.

Most probable explanation/sequence

Determine the most likely scenario (or sequence) given that you have an incomplete picture

Comparison query

Compare scenarios

Large networks

We have built networks with over 10000 variables

Parameter tuning

Automatically adjust your model to achieve a desired goal.

Soft/virtual evidence

Evidence can be uncertain on discrete variables

Custom data sources (API)

The API is so flexible you can connect to custom/bespoke data sources

Apache Spark

Bayes Server supports distributed processing on Apache Spark

Confusion matrix

Evaluate the performance of your model

Lift chart

Evaluate the performance of your model. Useful when the target is rare.

Residual plot

Evaluate the performance of your model


Does you current data have conflicting evidence?

Query explorer

Navigate large numbers of predictions/queries in the user interface

Exact and approximate inference

4 different advanced inference algorithms

Mutual information calculator

Multi-variate and conditional mutual information calculator (Discrete/continuous/hybrid).

Feature importance

Determine the most influential features from data


Advanced support for performing and dynamically displaying d-separation queries.

Entropy calculator

Multi-variate and conditional entropy calculator (Discrete/continuous/hybrid).

Kullback-Leibler divergence calculator

Multi-variate Kullback-Leibler calculator. (Discrete or continuous)

Tree width

Evaluate the complexity of your inference problem, given specific evidence and queries

Arc reversal

Reverse the direction of links in your network, while maintaining the same overall network distribution

Mesh query

Visualize predictions across 2 variables to easily identify patterns

Interventions (Do-Calculus)

Support for interventions on discrete, continuous and even temporal nodes.

Function nodes

Function nodes are evaluated after inference using potentially complex expressions.

Table expressions

Define table parameters based on potentially complex expressions

Relevance optimization

Our exact inference algorithms only touch what they need, increasing performance

Evidence propagation

Our inference algorithms can auto propagate evidence through deterministic distributions, improving performance

Disconnected networks

Networks can contain disconnected groups of nodes/variables