We assume in this page that your store is fully plugged to Beam, your models trained, and your business rules sharpened, all of the above saved under a scenario in your dashboard (keep in mind that an item-to-items scenario can not be used as user-to-items scenario, and vice versa)

The first step to deploy the recommendation on one of your stores is to create a widget that would be used on a specific page of your Shopify store.

Direct yourself to the widget section of your app

and click on “Add a widget.”

Configuring Your Widget

Shopify 2.0

If your store is a Shopify 2.0 store, you should then see the following section unfolding.

First thing you will want to focus on if the top part of this section, aka:

  • on what page would you like to deploy those recommendations?
  • What type of recommendations would you like to deploy? In other words, this also asks what input you would like the models to take into consideration to calculate the best recommendation:
  • is it a PdP, and would you like to consider the product id that the user is on - in which case you can select  “item-to-items”
  • or would you like the recommendations to be calculated based on the user profile and the session that is happening live, in which case you would select “user-to-items”
  • Let’s assume you selected “user-to-items”, you will now have to point out the scenarios that you’ve carefully crafted in your Beam Studio (alone or with the help of our team). You will have to do this both for existing and anonymous users, aka plugging your session-based scenarios.

Let’s assume, for example, that you want to deploy recommendations on your homepage and have defined some scenarios focusing on showing more new products for women (and have designed according to scenarios for this goal) - then your configuration will look as such.

Get started with Crossing Minds recommendation API

Crossing Minds Recommendation API is the easiest way to integrate personalized recommendation to your website & mobile apps

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
On this page
We use cookies (and other similar technologies) to collect data in order to improve our site. You have the option to opt-in or opt-out of certain cookie tracking technologies.To do so, click here.


API Documentation Center,
please wait a bit...