Unica Interact AutoBinning

In Interact, the built-in learning algorithm works partly by saving and analysing the values of profile attributes at the time offers were contacted and responded. Some attributes may have virtually unlimited number of unique values. However, due to limited resources in an Interact system, you can save only a small number of them. In addition, often it is more reasonable to do the analysis based on the ranges of the values. You can use this feature is to create such bins in Interact and the learning sub-system will automatically do the mapping.

You can create the bin definitions from Interact -> Global Learning -> All Bin Definitions page. While adding, or editing a bin definition you can select profile attributes from list of ALL attributes from all mapped profile tables. The types of a Bin Definition can be either Range or List. The “Range" type can only have mathematic operators, the “List" type can only have “contains" operator and consists of list of values.

Example for “Range" type bin:

low income < =30000

30000 < medium income < =60000

high income > 60000

Example for “List" type bin:

New England: MA, NH, CT

North West: MI, IL

A bin definition is global data across all interactive channels and across all learning models.

All bin definitions will be deployed as part of Global Deployment Data. You can deploy them in any interactive channel, deploying once and deployed for ALL. After that, the new bin definitions are saved into a memory cache, which is visible only to the built-in learning sub-system.

When a contact or response event is posted, the value of a profile attribute is mapped to a bin if such bin exists. The “bin" values is used while logging to the learning tables. If bins are defined for the attribute and the attribute value is not part of any bin definitions, then attribute value will be logged as OTHER in learning tables.