The affinity score is a percentile measure of how well a particular product fits the wants and needs of an individual contact. You can see the affinity score when you preview a product recommendation against a specific contact.

The affinity score is calculated in different ways, depending on which recommendation you're using. In general, trends in product characteristics and purchasing behaviour are used to determine which products to recommend to which contacts.

For the Best next recommendation, the affinity score shows how well the products fit the predicted contact journey. This is calculated based on which predicted products similar contacts bought in past purchases, and how many — this is called collaborative filtering.

For the Lookalike recommendation, the affinity score shows how similar products are to a contact's previous purchases. It's based on a product's characteristics, such as name, brand, colour, and type.