Leverage Coveo Machine Learning Product Recommendations (PR)

Ecommerce Developer Product Documentation

Coveo Machine Learning (Coveo ML) Product Recommendation (PR) models takes advantage of Coveo Usage Analytics (Coveo UA) to suggest relevant products to end users based on their past and present interactions with your Coveo-powered commerce implementation.

Coveo ML PR enhances your customers' shopping experience by offering them products that suit their profile, context, and buying behaviors. To provide relevant suggestions, the model continuously learns from your end users' feedback by scoping their buyer profile and analyzing their positive and negative interactions with different products. Thanks to its multiple algorithms, Coveo ML PR can easily adapt its approach to your digital commerce strategy.

Depending on your context, you can leverage one or more of the available PR strategies.

This article describes the prerequisites needed to create and deploy Coveo ML PR in a Coveo for Commerce search interface.

Product Recommendation model prerequisites

  1. Coveo Machine Learning (Coveo ML) Product Recommendations (PR) models use usage analytics (UA) events to relevantly target and suggest products to your customers. Therefore, you must log commerce events to ensure that your commerce interfaces correctly track user interactions.

  2. Depending on the recommendation strategy you want to leverage, ensure your commerce interface is tracking the proper events:

    Recommendation strategy Required events Optional events

    Cart recommender (cart)

    detail

    purchase

    None

    Frequently bought together (frequentBought)

    purchase

    refund

    add (to cart)

    remove (from cart)

    Frequently viewed together (frequentViewed)

    detail

    click

    Popular items (Bought) (popularBought)

    purchase

    refund

    Popular items (Viewed) (popularViewed)

    detail

    click

    User recommender (user)

    detail

    purchase

    refund

    add (to cart)

    remove (from cart)
Important

If there are less than 100 events available for your PR model, the model is empty and doesn’t provide recommendations. With 100 events or more, your model starts to learn and improve.

Create the Product Recommendation model

Once you ensured that your commerce interface tracks the proper usage analytics events, you can create a PR model.

Associate the Product Recommendation model with a query pipeline

Once your model has been created, you must associate your model with a query pipeline and select an appropriate strategy.

Query the desired Product Recommendation model

Once your model is associated with a query pipeline, you can then query the desired product recommendation model.