Use Case: Create an Automated Personalization Experience to Display Recommendations

You want to put an Automated Personalization experience on your site's product pages to serve recommendations. Variant A of the experience uses a recommendation strategy built with the Viewed and Also Viewed recommendation algorithm and filtering based on the gender of what products a customer is currently viewing. The recommendation strategy for variant B uses one of the Top Selling recommendation algorithms along with a static filter for items priced greater than $10. Additionally, you want to track engagement (clicks) with this recommendation as the goal metric for the experience.

Creating the Custom Event

The first step is to create a custom event to track customer clicks. Follow the steps in Creating the Custom Event in Track Customer Engagement with Recommendations to accomplish this task.

After you build the event, continue to the next section of this documentation to create the recommendation strategies.

Creating the Recommendation Strategies

This experience requires two different recommendation strategies:

• One strategy using the Viewed and Also Viewed recommendation algorithm based on the first item on the page and uses a dynamic filter for gender
• One strategy using the Top Selling by Purchase Count recommendation algorithm and a static filter for items with a price greater than $10

You can create the strategies in any order.

Creating the Viewed and Also Viewed Recommendation Strategy

Follow these steps to create the Viewed and Also Viewed strategy.

1. Click COMPONENTS in the top navigation bar, select Recommendations, and then click the Recommendations Strategies tab.

   

2. Click CREATE RECOMMENDATION STRATEGY.

   

3. Select the option on the Recommendation Strategy Permission modal to make the strategy either global so that it appears in all your accounts or local so that it's available only in the account in which you're working, and then click CONTINUE. To better understand how global and local settings work within strategies, see Global and Local Recommendation Strategies.

   You cannot change the strategy permission after you click CONTINUE.

   

4. Rename the new strategy. Click the placeholder title, type the new name into the text field, and then click the green checkmark.
5. If you're creating a local strategy and if the account has multiple product catalogs, select which one the strategy should use from Product Catalog.
6. Select Viewed and Also Viewed from Recommendation Algorithm.

   

7. Select Viewed from Base Recommendation on Items and then First Item on the Page from From.

   

8. Select from Lookback Period how much historical data you want the recommendation strategy to consider.

   

9. Optionally, toggle Randomize Results to YES if you want the order in which recommended products appear to be less systematized.
10. Click ADD FILTER and then scroll down to select Gender.

    

11. Click USE DYNAMIC VALUE.

    

12. Select Gender of Product Currently Being Viewed.

    

13. Click SAVE.

Continue to the next section to create the other recommendation strategy.

Creating the Top Selling by Purchase Count Recommendation Strategy

Follow these steps to create the Top Selling by Purchase Count strategy.

1. Repeat steps 1 through 5 from Creating the Viewed and Also Viewed Recommendation Strategy.
2. Select Top Selling by Purchase Count from Recommendation Algorithm.

   

3. If your implementation of the Monetate platform makes use of the Markets feature, then configure the Data comes from and, as applicable, Select a Market settings. See Create a Recommendation Strategy for Market-Level Recommendations for more information.

   

4. Select from Lookback Period how much historical data you want the recommendation strategy to consider.

   

5. Optionally, select an option from Geographic Targeting if you want the strategy to consider the customer's location to populate the recommendations:
   • Country targeting — Only products relevant to the customer's country are recommended
   • Region targeting — Only products relevant to the customer's region, as defined in MaxMind's GeoIP2 database, are recommended

   

6. Optionally, toggle Randomize Results to YES if you want the order in which recommended products appear to be less systematized.
7. Click ADD FILTER and then select Price.

   

8. Select > is greater than as the operator, and then type 10as the value to complete the filter equation.

   

9. Click SAVE.

After you create both recommendation strategies, you can create the Automated Personalization experience.

Creating the Automated Personalization Experience

Follow these steps to build the Automated Personalization experience.

Adding the Custom Event

Follow these steps to add the URL-tracking event as the primary metric to the experience.

1. Click EXPERIENCES in the top navigation bar and then select Web.
2. Click CREATE EXPERIENCE.

   

3. Click the pencil icon to the right of the placeholder name, give the new experience a name, and then click the green checkmark.
4. Click WHY, select Automated Personalization, and then click NEXT.

   

5. Select the event metric you created in Event Builder and then click NEXT.

   

6. Click NEXT to confirm the secondary metrics.

   

7. Click SAVE to confirm the WHY settings.

   

This experience should run for all visitors, so you don't need to change the For all visitors default setting for the WHO settings of the experience.

Continue to the next section to configure the WHAT part of the experience with the recommendation strategies.

Adding the Viewed and Also Viewed Recommendation Strategy

Follow these steps to create WHAT variant A that uses the Viewed and Also Viewed recommendation strategy.

1. Click variant A and then click ADD ACTION.

   

2. Click Recommendation on the Action Type panel, and then select a recommendations action template that includes the URL Parameter and URL Parameter Value fields.

   

3. Configure the settings in the Required Inputs section. Select from Recommendation Strategies the strategy that you created following the steps in Creating the Viewed and Also Viewed Recommendation Strategy.

   

4. Type the URL parameter name and URL parameter value that you used for the custom tracking event into URL Parameter Name and URL Parameter Value, respectively.

   

5. Click ADD CONDITION, select Page type, and then select Page type =.

   

6. Type product to complete the action condition so that the action only fires on product pages.

   

7. Click CREATE.

Continue to the next section to create variant B with the Top Selling by Purchase Count recommendation strategy.

Adding the Top Selling Recommendation Strategy

Follow these steps to create WHAT variant B that uses the Top Selling by Purchase Count recommendation strategy.

1. Hover your mouse pointer over the plus sign (+) under the Baseline field of the WHAT settings, click ADD VARIANT when it appears, select Variants With Actions From, and then select Unnamed Variant to copy the action you configured for variant A into variant B.

   

2. Click the field for variant B in the WHAT settings, and then click the recommendations action template title to edit the variant B action configuration.

   

3. Select from Recommendation Strategies the strategy that you created following the steps in Creating the Top Selling by Purchase Count Recommendation Strategy.

   

4. Click SAVE.

You can optionally add a label each to variant A and variant B to more readily identify which action is which.

1. Click the field in the WHAT settings for one of the variants, and then click the pencil icon that appears next to the variant's label placeholder text.

   

2. Give the variant a label and then click the green checkmark.

   

3. Repeat the steps to label the other variant.

The labels appear to the right of each variant field in the WHAT settings.

Continue to the next section to complete the experience.

Previewing and Activating the Experience

To complete the experience setup, configure the WHEN settings. See Configure Experience Timing for more information.

You should preview the experience before you activate it to ensure each variant appears as you want on your site. To do so, click PREVIEW, select Preview, and then click a viewing option.

When you're satisfied the experience is configured correctly, click ACTIVATE.

See Activate an Experience for Preview and Testing for more information.