Adding a filter to your marketing message allows you to send to a segment of the list who is most interested in the content of the message. Listrak enables you to segment your list based on many different criteria. 

One of these filter types is Predictive Analytics, which allows you to leverage what actions a contact may take in the future. Explore the additional filter types that can be used to segment your list.  

Listrak's Predictive Analytics allows you to create segments based on three different types of predictions: 

  1. Customer Lifetime Value
  2. Predicted Engagement 
  3. Purchase Behavior 

CUSTOMER LIFETIME VALUE

  • Predicted Lifetime Value: A calculation representing the amount a customer is likely to spend with your brand in the next 365 day

PREDICTIVE ENGAGEMENT 

  • Click: A measure of the likelihood that a customer has to click through a link in an email.
  • Open: A measure of the likelihood that a customer has to open an email.
  • Purchase: A measure of the likelihood that a customer has of making a purchase.
  • Unsubscribe: A measure of the likelihood that a customer has of unsubscribing from your email list.

PURCHASE BEHAVIOR 

  • Lifecycle Stage: A measure of a customer's position in their purchase lifecycle.
  • Coupon Affinity: Groups customers by the chance that they will use a coupon when making a purchase. Passing coupon information in the orders file is required to identify a buyer's coupon affinity. 
  • Discount Affinity: Groups customers by the chance that they will purchase an item using a discount. Passing discount information in the orders file is required to identify a buyer's discount affinity. 

TYPES OF CLASSIFICATIONS

Predictive models allow you to break down your customer list in a few different ways. The likelihood option breaks down each contact's list into four different groupings. Affinity options indicate the strength of a relationship. The Lifecycle Stage option classifies a contact based on where an individual customer is in their lifecycle.

LIKELIHOOD GROUPINGS

Likelihood classifications are based on comparing a specific customer's behavior to the average customer's behavior for a company. Likelihood classifications are available for Predicted Engagement models: click, open, purchase, and unsubscribe. 

All likelihood models measure the chance that a given behavior will occur in the next 14 days

  • Most: Identifies customers who are two times or more likely to complete a specific action.
  • More: Identifies customers who are more likely than the average customer and less than two times more likely to complete a specific action.
  • Less: Identifies customers who have between a 0.5 - 1x likelihood to complete a specific action.
  • Least: Identifies customers who have less than a 0.5x likelihood to complete a specific action. 

AFFINITY GROUPINGS

Affinity models identify the strength of a relationship a customer has with a purchase motivator. Affinity grouping are available for Coupon and Discount motivators. 

  • Coupon/Discount Buyer: 100% of purchases made using a coupon or discount. 
  • Coupon/Discount Preference: 50 - 100% of purchases made using a coupon or discount.
  • No Preference: 25 - 50% of purchases made using a coupon or discount.
  • Full Price Buyer: No purchases made using a coupon or discount.
  • Non-Coupon Buyer: No purchases made using a coupon. 

LIFECYCLE STAGES  

Listrak uses purchase behavior to identify the length of an individual customer's lifecycle, which is then used to measure a contact's likelihood to churn. If information is not available to identify a customized customer lifecycle, Listrak uses the lifecycle of the average customer until enough information is available to create a customized version. The length of a customer's lifecycle will vary based on their purchase habits. 

  • Active: Identifies customers who have made a recent purchase and are in the first half of their lifecycle.
  • At-Risk: Identifies customers who have not made a recent purchase and are in the second half of their lifecycle.
  • Churned: Identifies customers who have not purchased within their expected lifecycle.
  • Has Not Purchased: Identifies non-customers who do no have a lifecycle stage because they have not made a purchase.

PREDICTED LIFETIME VALUE 

  • Predicted Lifetime Value: A measure of the potential revenue a customer will generate for your brand in the next 12 months. 

ADDING FILTERS TO YOUR MARKETING MESSAGES 

Predictive filtering can be added anywhere filtering is available in the Platform, including, message-level filtering, split test filtering, on the contacts menu, and in Listrak Conductor conversations. 

Follow the below steps to add filters.

1. Click Edit Filter.
2. Select Predictive Analytics from the first drop-down menu. 

3. Select a predictive model from the second drop-down menu. 

4. Next, select if you would like to include or exclude the group of contacts.
NOTE: Your type of classification will pre-populate based on the model chosen. 

5. Then, select the specific group of contacts.

6. Select Update.
7. Click Apply Filter


Congratulations! Now you can add predictive filtering to your segmentation and filtering strategy. Check out Strategic Campaigns and Predictive Filters for some ideas on how to incorporate it into your strategy. 

Did this answer your question?