Promote discounted items to customers at risk of churn

If your customers are at risk of churn, you can increase the probability of discounted items appearing in their recommendations. Thanks to this, they are more likely to make a purchase.

This can be done by using recommendation boosting to promote discounted items. Boosting rules are built using the same editor as the filters, but unlike filtering, boosting does not entirely exclude items that do not meet the conditions - it only tells the AI model to assign more weight to the discount value parameter when calculating the final recommendation score (relevance to a particular customer) of an item.

Prerequisites

1. Recommended: Become familiar with creating recommendations and recommendation filters (using the IQL query editor).
   This article does not explain every step of creating a recommendation in detail.
2. The item feed must contain information about discounts. In this example, the discount is defined as a percentage.
3. Predict churn for a group of customers.
   The Predict churn use case includes detailed instructions.
4. Create a segmentation of customers for whom the score-label parameter in the snr.prediction.score event from the prediction was high or very high.
   This segment of customers will be needed to set up the boosting conditions.
   Learn more about creating segmentations.

Creating the recommendation

Choose source, type, and add slots

1. Go to Communication > Recommendations > Add recommendation.
2. In the Type & Items feed section:
   1. Select an item catalog.
   2. Select a recommendation type.
      Tip: Boosting can be used with all recommendation types.
   3. Click Apply.
3. In the Items section, configure at least one slot and click Apply.

Build the boosting rule in IQL query editor

In this part of the process, you build the following rule:

• If the customer is at risk of churn, filter the boosting to only apply to items that are discounted 10% or more.
• If the customer is NOT at risk of churn, apply boosting to all items (so, effectively, no items are boosted).

1. In the Boosting section, click Define.
2. Click Add rule.
3. Click Define rule and select IQL query.
   Result: The IQL query editor opens.
4. Click Select > Function.
5. Click the added function and select IF.
   The IF function accepts three variables, from the left: the condition, the result if the condition evaluates to TRUE, and the result if the condition evaluates to FALSE.
6. Add the condition that customer must be at risk of churn:
   1. Click the first Select node and select Segmentation.
   2. To the right from client.segmentations, click the plus icon and select Attribute.
   3. Click the null element that appeared.
   4. From the Property drop-down list below the canvas, select Segmentation.
   5. Click Select value and select the segmentation that includes customers at risk of churn.
      You can use the search field.
   6. Click the plus icon between client.segmentations and the segmentation ID and select the CONTAINS operator.
7. Add the if TRUE result:
   1. Click the Select node and select Attribute.
   2. Click the null element that appeared.
   3. In the attribute selector below the canvas, click Select value.
   4. Select the discount percentage attribute.
      You can use the search field.
   5. To the right from the attribute node, click the plus icon and select Number.
   6. Click the plus icon between the attribute and the number and select the operator.
   7. In the Number input field below the canvas, enter 10.
8. Add the if FALSE result:
   1. Click the Select node and select Take All.
9. Click Apply.
10. In the Promote/Demote selector, select Promote (default value).
11. Use the slider to adjust how much you want the rule to affect the results.

    

12. Save the Boosting section settings by clicking Apply.
    
    Tip: After applying the settings, you can use the Preview tab (available in the upper left part of the recommendation creator screen) to see how your rule changed the recommendation result. If necessary, you can return to the settings and adjust the boosting strength to meet your expectations.

Additional settings and saving

1. Configure the Additional settings section and click Apply.
2. Save the recommendation.

What’s next

You can use the ID of the recommendation and insert it in other types of communication, such as:

• dynamic content - this way you can show the recommendations on your website.
• email - this way you can send out recommended items through emails.
• mobile application - you can use documents to build your own mobile app and show the recommended items.
• mobile push - you can send recommendations through notifications in your mobile application.
• web push - this way you can send notifications to your customers through a web browser.
• SMS - this way you can reach your customers with recommendations on their mobile.

Read more

• Recommendations