The available models for personalized recommendations using Engage is continuously growing and new models will be documented here as they become generally available. If you need something currently not covered here, reach out directly to us for support to arrange that.

Model overview

  • Others also bought

  • Similar items for you

  • Recently viewed items

  • Clustered Similarity BETA

  • Rule Based Models BETA

Data requirements and workarounds

While all models require data, our models are developed to perform well even when data is sparse or insufficient. This can happen when new products are introduced, a merchant recently opened shop, or because of data loss when moving shops between platforms. Regardless of why there is a data shortage our models can for example aggregate data to create recommendations on an aggregated, a bit less granular level until there is a sufficient amount of data available. Other models can run solely on for example product data and thereby runs well with basic catalog data.


Others also bought

This model uses historical data to derive purchase patterns and relate them to users and items to predict what any given user is likely to be interested in based on browsing pattern and purchase history (when available). This model is generally great on cart pages, product pages or at checkout.

Similar items for you

The similarity model is useful to display visually, textually or contextually similar products, like clothes or accessories. The model is commonly used on product detail pages to help the visitor find the product they are looking for. The model is not as data intense as other models since it mainly rely on product data. This model generally increase conversion and decrease bounce rates on the product page when visitors are coming directly to a product page from an external source, such as ads.

Last updated