Provides several algorithms: such as Naive Bayes and Adaptive Bayes Networks for Classifications, Enhanced K-Means and O-Cluster for Clustering, Association Rules for finding patterns of co-occurring events, and Attribute Importance for reducing the size of the source data
- Classification: Classification algorithms can predict binary or multi-class outcomes. In binary problems, each record either will or will not exhibit the modeled behavior. For example, a model could be built to predict whether a customer will churn or remain loyal. These algorithms can also make predictions for multi-class problems where there are several possible outcomes. For example, a model could be built to predict which class of service will be preferred by each prospect.
- Binary model example:
Q: Is this customer likely to become a high-profit customer?
A: Yes, with 85% probability
- Multi-class model example:
Q: Which one of five customer segments is this customer most likely to fit into Grow, Stable, Defect, Decline or Insignificant?
A: Stable, with 55% probability
- Association Rules: Association Rules detect "associated" or co-occurring events hidden in databases. Association analysis, or unsupervised learning, is often used to find popular bundles (e.g. market basket analysis) of products that are related for customers, such as "milk" and "cereal" being associated with "bananas." The Association Rules algorithm generates a set of antecedent and consequent pairs in the form of A implies B with a probability of n%. This modeling technique allows users to discover associations between items or events. Association Rules can be used to identify co-occurring items or events in a variety of business problems, such as which patient and drug attributes are associated with which outcomes?
Return to top