Create a Recommendation Strategy with Offline Purchases Data

Follow these steps to create a recommendation strategy that uses data from the Offline Purchases dataset set as the default on the Global Recommendation Settings tab.

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

   

2. Click CREATE RECOMMENDATION STRATEGY.

   

3. Select the option on the Recommendation Strategy Permission modal to make the strategy either global or local, and then click CONTINUE. For more information see Global and Local Recommendation Strategies.

   You cannot change the strategy permission after you click CONTINUE.

   

4. Name the strategy. Click the placeholder title, type the 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, then select one from Product Catalog.

   

6. Select from Recommendation Algorithm one of the algorithms that's eligible for use with offline purchases data:
   • Top Selling by Purchase Count
   • Top Selling by Gross Revenue
   • Purchased and Also Purchased
   • Trending Items by Purchase Count (premium algorithm)

   

7. Select either Offline purchases only or Online and offline purchases from Including.

   

8. If you selected Purchased and Also Purchased in step 6, then select from Base Recommendation on the type of customer behavior or other context on which to base the recommendations.

   The Item group ID(s) in custom variable option that allows you to base recommendations on item_group_id values passed at run time in custom variables is part of the Premium Product Recommendations package. Contact your dedicated Customer Success Manager (CSM) for more information.

   The Item group ID(s) in run-time parameter (for email) option is part of the Product Recommendations for Email add-on to the Premium Product Recommendations package. Contact your dedicated Customer Success Manager (CSM) for more information. If you select this option, you can use up to five item_group_id values passed in a run-time parameter for a Product Recommendations for Email experience. See Preparing the Generated HTML in Run-Time Context for Recommendations Email Experiences.

   

9. If you selected Item group ID(s) in custom variable in step 8, then take the following actions.
   1. Optionally, select Pin products in custom variable to front of recommendation results if you want the products corresponding to the item_group_idvalue(s) derived from the custom variable to appear at the beginning of the recommendation results.

      If you select this option, be aware that pinned products configured in the recommendation strategy appear after any pinned products configured in a recommendations action that uses the recommendation strategy.

      

   2. Type into Custom Variable a custom variable that your site passes to Monetate using either the setCustomVariables method call in the Monetate API implementation or the monetate:context:CustomVariables in the Engine API implementation.

      The custom variable value can contain a comma-separated list of up to five item_group_id values.

      

10. If you selected Item group ID(s) in run-time parameter (for email) in step 8, then optionally select Pin products in run-time parameter to front of recommendation results.

    If you select this option, be aware that pinned products configured in the recommendation strategy appear after any pinned products configured in a recommendations action that uses the recommendation strategy.

    

11. If you selected any recommendation algorithm except for Trending Items by Purchase Count in step 6, then select an option from Lookback Period to set how much historical data the strategy considers when calculating results.

    

12. If you selected Top Selling by Purchase Count or Top Selling by Gross Revenue in step 6, then optionally select an option from Geographic Targeting if you want the strategy to also 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

    

13. Optionally, toggle Randomize Results to YES if you want the order in which recommended products appear in the slider to be less systematized.

    

14. To further refine the recommendations results, click ADD FILTER, select an option from SELECT ATTRIBUTE, and then complete the filter equation. Repeat this step as necessary to add as many recommendation filters as you believe the strategy needs. See Excluding Previously Purchased Products from Results in this documentation if you want to ensure results don't include items the customer has already bought.

    

15. Optionally, configure up to five Boost and Bury filters to influence if recommended products that meet that filtering criteria are more likely (boost) or less likely (bury) to appear for the customer.

    Contact your dedicated CSM if you want the Boost and Bury feature enabled.

    1. Click ADD ATTRIBUTE and then select an attribute.

       

    2. Complete the filtering equation.

       

    3. Select Boost to promote the products that meet the filtering criteria, or select Bury to suppress them.

       

    4. Adjust the slider to determine by what percentage the products that meet the filtering criteria are boosted or buried.

       You can only set the percentage using the slider and cannot type a number into the text field to the left it. Furthermore, you can only adjust the percentage in increments of 10.

       

    5. Repeat steps 15a through 15d to add up to four more independent Boost and Bury filters. See Using Multiple Boost and Bury Filters in Create a Recommendation Strategy for more information about how multiple Boost and Bury filters can impact recommendations results.

       

16. Click SAVE.

    

Excluding Previously Purchased Products from Results

Follow these steps to create a recommendation filter that specifically excludes previous purchases from the recommendations results.

1. Click ADD FILTER, and then select either Item Group ID (Product ID) or ID (SKU) from SELECT ATTRIBUTE.

   

2. Select ≠ does not equal for the operator.

   

3. Click USE DYNAMIC VALUE.

   

4. Select [attribute] of a Previously Purchased Product.

   

This filter configuration excludes from the recommendations results both products purchased online and products purchased in store that appear in the designated Offline Purchases dataset.