Machine Learning

Predictive Lifetime Value

The Predictive Lifetime Value (PLTV) model predicts the revenue or margin of a customer in the next 12 months. The model predicts potential future value of customers and allows you to build campaigns around the predicted buying behavior.

Use cases

VIP treatment of high PLTV customers

  • Create an enhanced marketing journey (for example, store associate outreach) for such customers.

  • Design special offers and in-store events.

  • Send a gift that accounts for surprise and delight.

Direct mail to high PLTV customers

Limit direct mails to the top tiers to maximize ROI and cut losses on lower tiers.

Spend optimization

Target high PLTV customers with discount bundle deals to increase ticket size.

Customer comprehension

Understand your new customers by pivoting PLTV groups with other dimensions such as demographics, acquisition source or machine learning dimensions like Likelihood To Buy, Likelihood To Pay Full Price.

Target audience

The PLTV model predicts the behavior of buyers. A buyer is a customer with a transaction in the past three years. Hence, anyone who hasn’t bought an item in the last three years isn’t included in this model.

How does the model work?

For each contact, the model calculates:

  • the purchase behavior features such as lifetime value, recency, frequency, and Average Order Value (AOV)

  • the email behavior features such as send, open, click frequency, volume, and recency

  • the web behavior features such as browse or abandoned cart counts, session duration, session recency

CDP trains and tests the model on historical data where the outcome is known. Post training, the model is deployed to predict future revenue.

This model ouputs the following sets of values:

  • Predictive lifetime value - this is the actual prediction for the customer

  • Predictive lifetime value decile

  • Predictive lifetime value revenue group

By default, predictive value decile is split into 22 buckets:



01, 02


03, 04, 05, 06, 07, 08, 09


10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20



Non buyer


Not qualified

Predictive value revenue group has the following default intervals:

  • 01 - 3000+

  • 02 - 2000-3000

  • 03 - 1500-2000

  • 04 - 1000-1500

  • 05 - 500-1000

  • 06 - 200-500

  • 07 - 100-200

  • 08 - 50-100

  • 09 - 1-50

  • 10 - 0

Deciles higher than 10 (for example, 11, 12) have low predictive value.

Using the PLTV model

CDP displays the output from the PLTV model in:

  • 360 > 360 Profiles

  • Actions > Campaigns and Actions > Campaigns+

  • Analytics > Metrics

You can use the top five revenue groups as additional filters for:

  • Pushing information to Facebook as it is an expensive channel. Hence, you can run daily campaigns that send information to Facebook to target high PLTV customers.

  • Sending direct mails to audience lists through ad-hoc campaigns. Thus, you can limit the audience to high PLTV customers.

To review the continued effectiveness of the model, you can use a dashboard to compare the six-month older predictive lifetime revenue groups with the actual purchases in the last six months.

To learn more about how the Predictive Lifetime Value (PLTV) model can enhance your marketing workflow, contact us.