MS Association Rules Node

The MS Association Rules modeling node is useful for recommendation engines. A recommendation engine recommends products to customers based on items they have already purchased or in which they have indicated an interest. Association models are built on datasets that contain identifiers both for individual cases and for the items that the cases contain. A group of items in a case is called an itemset.

An association model is made up of a series of itemsets and the rules that describe how those items are grouped together within the cases. The rules that the algorithm identifies can be used to predict a customer's likely future purchases, based on the items that already exist in the customer's shopping cart.

For tabular format data, the algorithm creates scores that represent probability ($MP-field) for each generated recommendation ($M-field). For transactional format data, scores are created for support ($MS-field), probability ($MP-field) and adjusted probability ($MAP-field) for each generated recommendation ($M-field).

Requirements

The requirements for a transactional association model are as follows:

• Unique field. An association rules model requires a key that uniquely identifies records.
• ID field. When building an MS Association Rules model with transactional format data, an ID field that identifies each transaction is required. ID fields can be set to the same as the unique field.
• At least one input field. The Association Rules algorithm requires at least one input field.
• Target field. When building an MS Association model with transactional data, the target field must be the transaction field, for example products that a user bought.