Create a Recommendation Strategy with a Recommendations Dataset

Follow these steps to create a recommendation strategy that uses a Recommendations dataset.

See the Recommendations Datasets category of the knowledge base for dataset specifications and steps to upload one to the Monetate platform.

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

    Callout of the Recommendations Strategies tab on the Product Recommendations page

  2. Click CREATE RECOMMENDATION STRATEGY.

    Callout of the CREATE RECOMMENDATION STRATEGY button on the Recommendation Strategies list page

  3. Select the option on the Recommendation 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.

    The Recommendation Permission modal of the recommendation strategy configuration page

  4. Name the strategy. Click the placeholder title, type the name into the text field, and then click the green checkmark.

    This field can contain a maximum of 64 characters.

  5. If you're creating a local strategy and if the account has multiple product catalogs, then select one from Product Catalog.

    Callout of the Product Catalog selector on the recommendation strategy configuration page

  6. Select Onboarded Recommendation Dataset from Recommendation Algorithm.

    Callout of the 'Onboarded Recommendation Dataset' option in the Recommendation Algorithm selector on the recommendation strategy configuration page

  7. Select the dataset you want to use from Recommendation Dataset.

    Callout of the Recommendation Dataset selector that appears when the user selects 'Onboarded Recommendation Dataset' from the 'Recommendation Algorithm' selector on the recommendation strategy configuration page

  8. Select from Base Recommendation on the type of customer behavior or other context on which to base the recommendations.

    If you're creating the recommendation strategy to use in a Product Recommendations for Email experience, then you can select only No Lookup Key — Show All Items in Dataset or Item group ID(s) in run-time parameter (for email). The latter option allows you to use up to five item group ID values in the Product Recommendations for Email experience. See Preparing the Generated HTML in Run-Time Context for Recommendations Email Experiences.

    The Item group ID(s) in custom variable option allows you to base recommendations on item_group_id values passed at run time in custom variables. This option isn't compatible with Product Recommendations for Email experiences.

    Callout of the 'Base Recommendation on' selector on the recommendation strategy configuration page

  9. Optionally, toggle Prepend context item in recommendation to YES if you want the product on which the recommendation results are based to appear at the beginning of the recommendation results.

    If you enable this option, be aware that the context product appears after any pinned products configured in a recommendations action that uses the recommendation strategy.

    Callout of the 'Prepend context item in recommendation' setting on the recommendation strategy configuration page

  10. If you selected Item group ID(s) in custom variable in step 8, then 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.

    Callout of the 'Custom Variable' field on the recommendation strategy configuration page

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

    Callout of the 'Randomize Results' toggle on the recommendation strategy configuration page

  12. To further refine the items included in the strategy, 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. For more information see Filters in Recommendations.

    Animated demonstration of a user clicking the ADD FILTER button, typing 'product' into the search field of the SELECT ATTRIBUTE selector, and then selecting the 'Item Group ID (Product ID)' option

  13. 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. See Boost and Bury for more information.

    Animated demonstration of a user moving the slider to adjust the boost percentage

  14. Click SAVE.

    Callout of the SAVE button

After you save the strategy, you can preview it from the configuration page in certain situations. See Preview a Recommendation Strategy for more information.

Related Articles