Likelihood To Pay Full Price

The Likelihood To Pay Full Price (LTPFP) model predicts near-future discounting behavior based on past transaction, email, and browsing behavior. This model helps marketer to know the probability of a customer buying a certain product in the near future with zero or low discount.

Use cases

Pricing optimization

Give lower discounts to the customers that are likely to pay full price. Alternatively, you can give higher discounts to the customers that are unlikely to purchase without a high discount. Thus, you can stop cannibalizing margin on the former while earning incremental revenue on the later.

Revenue optimization

Recommend full price items to those with high likelihood to pay full price while you can recommend sale items to those with a lower likelihood to pay full price.

Likelihood to pay full price can also be combined with other machine learning models, such as Predictive Lifetime Value, to design bundle campaigns for the high predictive lifetime value customers that also have high likelihood to pay full price.

Loyalty and discount optimisation

While promoting a “global” discount coupon for all customers, exclude the customers with high likelihood to pay full price.

Customer analytics

Identify the customers with high likelihood to pay full price and merge them with other machine learning predictions, such as Likelihood To Buy, Likelihood to Convert, to build new segments.

Target audience

The LTPFP model predicts the behavior of buyers. A buyer is a customer with a transaction in the past three years. Hence, anyone who has bought earlier than 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 margin, total discount, discount rate, and ratio of full price items
  • the email behavior features such as send, open, and click of emails promoting sales
  • the web behavior features such as browse or abandoned cart counts, especially of discounted items

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

The output of the model is the likelihood to pay full price for each customer. This probability is segmented in 10 equal-sized deciles, 1 being the most likely decile to yield full price buyers:

Decile Description
1, 2 High
3, 4, 5 Medium
6, 7, 8, 9, 10 Low
NA Non buyer
NA Not qualified

Using the LTPFP model

CDP displays the output from the LTPFP model in:

  • 360 > 360 Profiles
  • Actions > Campaigns and Actions > Campaigns+
  • Analytics > Metrics

To learn more about how the Likelihood To Pay Full Price (LTPFP) model can enhance your marketing workflow, contact us.