Voyado Elevate

How recommendation types behave in Elevate

Different recommendation types behave differently depending on ranking, stock, personalization and merchandising rules. This article explains how recommendation types interact with Elevate’s ranking and recommendation logic.

Use the table below to understand the behaviour of each recommendation type before adding it to a Recommendation List. Each column describes a specific characteristic that may affect how results appear on your site.

Recommendation typeIncludes out-of-stock productsAffected by missing imageAffected by Exposure strategyAffected by Boost/BuryFill up slotsSoft deduplication
Top productsYes *Yes *YesYesYesYes
PersonalNoYesYesPartiallyYesYes
AlternativesNoYesYesPartiallyNoYes
UpsellNoYesNoPartiallyYes **Yes
CartNoYesYesPartiallyYesYes
Style withNoYesNoNoNoNo
FavoritesNoYesYesPartiallyYesYes
Newest productsYes *Yes *NoNoYesNo
More from seriesYes *Yes *YesPartiallyNoYes
Recently viewedYesNoNoNoNoNo
Add-to-cart recommendationsNoYesNoPartiallyNoYes

* Out-of-stock and missing-image products are included but demoted according to the setting Out of Stock / Bury Missing Image in the Elevate application.

** Upsell can return an empty result if no in-stock products exist within the same gender and age groups, but this is very rare.

Partially (Boost/Bury) means the algorithm is influenced, but other strong signals (e.g. personal affinity) may limit the visible effect. Both Boost/Bury and Exposure strategy affect the same algorithms, as both work by adjusting a product's entity score.

Fill up slots means the recommendation practically always has something to show (within any applied filter).

Soft deduplication means that Elevate tries to reduce repeated products across recommendation lists when possible. 

Article last updated