Predicted_CLV_Attributes Table

The Predicted_CLV_Attributes table contains information, for each individual Amperity ID, about predicted future spend and the probability of churn.

Note

The size of the Predicted_CLV_Attributes table in your tenant is based on the number of Amperity IDs.

Add table

Add the Predicted_CLV_Attributes table to the customer 360 database.

as a SQL table

A SQL table adds a table to the customer 360 database using Spark SQL and a SELECT statement to define the table’s schema.

The days_since_last_order and historical_order_frequency_lifetime columns in the Predicted_CLV_Attributes table are not recommended for use with segmentation or for downstream workflows. Use SQL to build a predicted attributes table for use in the customer 360 database that omits these columns.

To add the Predicted_CLV_Attributes table as a SQL table

  1. From the Customer 360 tab, under All Databases, select the menu for the customer 360 database, and then click Edit.

  2. From the Database Editor, click Add Table.

  3. Set Build Mode to “SQL”, and then use a SELECT statement similar to the following to define the schema:

    SELECT
      amperity_id AS `amperity_id`
      ,predicted_average_order_revenue_next_365d AS `average_revenue_365`
      ,predicted_clv_next_365d AS `clv_365`
      ,predicted_customer_lifecycle_status AS `purchase_likelihood`
      ,predicted_customer_lifetime_value_tier AS `value_tier`
      ,predicted_order_frequency_next_365d AS `predicted_orders_365`
      ,predicted_probability_of_transaction_next_365d AS `purchase_probability`
    FROM Predicted_CLV_Attributes
    
  4. Hide the table from the Visual Segment Editor by verifying that Show in VSE? is unselected.

  5. Click Activate to update the customer 360 database with your changes.

as a passthrough table

A passthrough table adds a table to the customer 360 database using an existing table without making any changes to its schema.

To add the Predicted_CLV_Attributes table as a passthrough table

  1. From the Customer 360 tab, under All Databases, select the menu for a database, and then click Edit.

  2. Click Add Table.

  3. Set Build Mode to “passthrough”, and then select the Predicted_CLV_Attributes table from the drop-down menu.

  4. Hide the table from the Visual Segment Editor by verifying that Show in VSE? is unselected.

  5. Click Activate to update the customer 360 database with your changes.

Column reference

The Predicted_CLV_Attributes table contains the following columns:

Column Name

Data type

Description

amperity_id

String

The unique identifier that is assigned to clusters of customer records that all represent the same individual. The Amperity ID does not replace primary and foreign keys, but exists alongside them within unified profiles.

Note

The Amperity ID is a universally unique identifier (UUID) that is represented by 36 characters spread across five groups separated by hyphens: 8-4-4-4-12.

For example:

123e4567-e89b-12d3-a456-426614174000

predicted_average_order_revenue_next_365d

Decimal

The predicted average order revenue over the next 365 days.

predicted_clv_next_365d

Decimal

The total predicted customer spend over the next 365 days.

predicted_customer_lifecycle_status

String

A probabilistic grouping of a customer’s likelihood to purchase again.

For repeat customers, groupings include the following tiers:

  1. Active (likelihood to purchase is greater than 60%)

  2. Cooling down (likelihood to purchase is between than 50% and 60%)

  3. At risk (likelihood to purchase is between than 35% and 50%)

  4. Highly at risk (likelihood to purchase is between than 20% and 35%)

  5. Lost (likelihood to purchase is less than 20%)

For one-time buyers, groupings include the following tiers:

  1. Active (purchased within 60 days)

  2. Cooling down (purchased 60-120 days ago)

  3. At risk (purchased 120-180 days ago)

  4. Highly at risk (purchased 180-240 days ago)

  5. Lost (purchased 240+ days ago)

predicted_customer_lifetime_value_tier

String

A percentile grouping of customers by pCLV. Groupings include:

  1. Platinum: top 1% of customers

  2. Gold: top 1%-5% of customers

  3. Silver: top 5%-10% of customers

  4. Bronze: top 10%-25% of customers

  5. Medium: top 25%-50% of customers

  6. Low: bottom 50% of customers

predicted_order_frequency_next_365d

Decimal

The predicted number of orders over the next 365 days.

predicted_probability_of_transaction_next_365d

Decimal

The probability a customer will purchase again in the next 365 days.