Recommendation model types

This page describes the recommendation types, or models, provided by Recommendations AI, with their default placements and optimization objectives, available customizations, and supported event types.

Introduction

When you sign up to use Recommendations AI, you work with Recommendations AI Support to determine the best recommendation models and customizations to use for your site. The models and customizations you use depend on your business needs, and where you plan to display the resulting recommendations.

When you request recommendations from Recommendations AI, you provide the placement value, which determines which model is used to return your recommendations. You can also filter your results.

Available recommendation types

Recommendations AI offers the following recommendation model types:

Others you may like

The "Others you may like" recommendation predicts the next product that a user is most likely to engage or convert with. The prediction is based on the viewing history of the user and the candidate product's relevance to a current specified product.

Default optimization objective: click-through rate

Default placement: product_detail

Available customizations:

Supported user event types:

Frequently bought together (shopping cart expansion)

The "Frequently bought together" recommendation predicts items frequently bought together for a specific product within the same shopping session. If a list of products is being viewed, then it predicts items frequently bought with that product list.

This recommendation is useful when the user has indicated an intent to purchase a particular product (or list of products) already, and you are looking to recommend complements (as opposed to substitutes). This recommendation is commonly displayed on the "add to cart" page, or on the "shopping cart" or "registry" pages (for shopping cart expansion).

Default optimization objective: revenue per order

Default placement: shopping_cart

Available customizations:

Supported user event types:

Recommended for you

The "Recommended for you" recommendation predicts the next product that a user is most likely to engage with or purchase, based on the shopping or viewing history of that user. This recommendation is typically used on the home page.

"Recommended for you" can also be useful on category pages. A category page is similar to a home page, except that you display only items from that category. You can achieve this using a standard Recommended for you model with filter tags. For example, you can add customized filter tags (corresponding to each category page) to the items in your catalog. When you send the prediction request, set the user event object as category-page-view and specify a specific category page's tag in the `filter` field. Only recommendation results matching the requested filter tag are returned. Diversity should be disabled in this use case, because diversity can conflict with category-based filter tags.

Default optimization objective: click-through rate

Default placement: home_page

Available customizations:

Supported user event types:

Recently viewed

The "Recently viewed" recommendation is not actually a recommendation. It provides the catalog IDs of items the user has recently interacted with, with the most recent items first.

Default optimization objective: N/A

Default placement: recently_viewed_default

Available customizations: N/A

Supported user event types:

All

Optimization objectives

Machine learning models are created to optimize for a particular objective, which determines how the model is built. Each model placement has a default optimization objective, but you can request a different optimization objective to support your business goals by contacting your support representative.

After you have trained a model, you cannot change the optimization objective. You must train a new model to use a different optimization objective.

Recommendations AI supports the following optimization objectives:

Click-through rate (CTR)

Optimizing for CTR emphasizes engagement; you should optimize for CTR when you want to maximize the likelihood that the user interacts with the recommendation.

CTR is the default optimization objective for the "Others you may like" and "Recommended for you" recommendation model types.

Revenue per order

The revenue per order optimization objective is the default optimization objective for the "Frequently bought together" recommendation model type. This optimization objective cannot be specified for any other recommendation model type.

Conversion rate (CVR)

Optimizing for conversion rate maximizes the likelihood that the user adds the recommended item to their cart; if you want to increase the number of items added to a cart per session, optimize for conversion rate.

Advanced model configuration options

Depending on the model type, there are some other model configuration options you can use to change the behavior of your model.

Diversification

If you want to ensure that results returned from a single prediction request are from different categories of your product catalog, you can enable diversification.

Diversification reduces the likelihood that similar catalog items are shown in the recommendation panel, at the risk of removing some good recommendations. Diversification is configured by level, with higher levels of diversification causing fewer items to be displayed per category.

Diversification level Max items per category Default
Off Unlimited Others you may like
Frequently bought together
Auto Depends on catalog Recommended for you
Low 3 -
Medium 2 -
High 1 -

Auto is supported only for the "Recommended for you" recommendation model.

Price reranking

For the "Others you may like" and "Recommended for you" recommendations, you can enable price reranking. Price reranking causes recommended catalog items with a similar recommendation probability to be ordered by price, with the highest- priced items first. (Because relevance is also used to order the items returned, enabling price reranking is not the same as sorting by price.)

Enabling price reranking helps balance conversion rates and average order values. Price reranking is disabled by default.

Tuning preference

Tuning keeps model training optimal as input data changes over time. Set your model to automatically tune every three months, or choose to only tune it manually. The model automatically tunes one time after creation. Learn more.

Results filtering

You can filter the prediction results for a placement by the tag value you provided with the catalog item and by whether the item is in stock. Learn more.

Available placements

Before you can request predictions from your model, you must create at least one placement for it. For more information, see Managing recommendation placements.

You can see your models listed on the Models page. Click a model name to go to its details page, where you can see placements associated with that model.