Predictive models

A predictive model is a feature of AmpIQ that predict customer behavior, such as predicted customer lifetime value (predicted CLV), churn propensity, product affinity, and lifecycle events.


Predictive models require at least four years of historical data (five years or more is recommended). You should have at least 100,000 customer transactions on an annual basis, with at least a 10% retention rate.

The following tables must be configured in your customer 360 database prior to running predictive models:

  1. Customer 360

  2. Merged Customers

  3. Transaction Attributes

  4. Transaction Attributes Extended

  5. Unified Itemized Transactions (updated to include product catalogs)

  6. Unified Transactions

Amperity Learning Lab

Amperity Learning Lab

Amperity provides a set of predictive models.

Churn propensity predicts the likelihood of customer activity. Predicted CLV predicts the order value for purchases made within the next year. Product affinity predicts who is likely to purchase.

Open Learning Lab to learn more about how predictive modeling can help your brand. Registration is required.

Common inputs to models

Columns from the Merged Customers, Unified Transactions, and Unified Itemized Transactions (including product catalogs) are used as inputs to predictive modeling. For multi-brand tenants, the amperity_id column from the Customer 360 table is also used as an input to predictive modeling.

The following columns are common inputs to predictive models:

Source table

Input columns

Merged Customers

The following columns are common inputs:

  • amperity_id

  • birthdate

  • city

  • email

  • gender

  • given_name

  • phone

  • postal

  • state

  • surname

Unified Itemized Transactions

The following columns are common inputs:

  • is_return

  • item_quantity

  • item_revenue

  • order_datetime

  • order_id

  • product_id

Unified Transactions

The following columns are common inputs:

  • amperity_id

  • order_canceled_quantity

  • order_canceled_revenue

  • order_datetime

  • order_discount_amount

  • order_id

  • order_quantity

  • order_returned_quantity

  • order_returned_revenue

  • order_revenue

  • purchase_brand

  • purchase_channel

  • store_id

Available models

The following predictive models can be enabled for your tenant: