The Behavior Clusters model groups users in homogeneous groups based on their buying behavior. This model generates a set of cluster IDs and cluster names, and assigns scored users to individual clusters.
Structure your programs better by defining personas. Clustering offers dimensionality reduction as you have to define your messaging for five or six customers and not millions.
The Behavior Clusters model predicts the behavior of buyers.
For each contact, the model calculates the purchase behavior features such as lifetime value, recency, frequency, and aov.
Clusters are assigned different cluster names based on the exhibited purchase behavior features. For example, a high lifetime order value indicates that the customer is a VIP, and a medium order value with high average discount indicates that customer is a discount seeker.
The model binds historical data multiple times using a range of values for clusters. It also generates various graphs and metrics, and uses them to determine the clusters that can be used for scoring. The goal is to have stable and meaningful clusters that exhibit reasonable statistical difference in the purchase behavior.
The name of the assigned clusters are displayed in the CDP user interface.
CDP displays the cluster names in:
To learn more about how the Behavior Clusters model can enhance your marketing workflow, contact us.