User Engagement

Prev Next

The User Engagement algorithm recommends products by analyzing the current user’s most recent interactions. It generates personalized recommendations based on real-time behaviors and evolving preferences.

The User Engagement algorithm tailors product recommendations based on the user’s latest product viewing activity, utilizing a deep learning-based transformer model that dynamically adapts to recent interactions like viewing or purchasing patterns. It focuses specifically on items the user has shown interest in during recent sessions. During the Smart Recommender API request to the user-engagement endpoint, a call is made to the profile endpoint of the UCD to retrieve the last 10 products the user visited within the past 7 days. To receive User Engagement recommendations, the user must have at least one product visit in the last 7 days. If there have been no visits in that period, fallback recommendation results will be displayed instead.

Endpoint

GET https://recommendation.api.useinsider.com/v2/user-engagement

Query Parameters

ParameterSample ValueDescriptionData TypeRequired
partnerNamemybrandPartner Identifier assigned by Insider. You can use PartnerID as well.StringYes
localeus_USLocale of requested product catalogStringYes
platformwebRequested platform. Web comes by default.EnumNo
userIda1b2c3d4User identifier which is assigned by InsiderStringYes
currencyUSDRequested currency of the products. If no value is set, the default currency in your settings is used.StringYes
size50Required number of items in response. Valid values are 0 to 100.IntegerNo
categoryList[“Clothes”, “Skirts”]Category filter of the productsArray (of string)No
filter
Smart Recommender filtering. There can be more than one filter parameter.StringNo
detailstrueAdds details to the products of the responseBooleanNo
shufflefalseShuffles the products of the responseBooleanNo
getGroupProductsfalseDetermines if the products within the same groupcode should be returned in the recommendation responseBooleanNo
groupProductsFields
Defines the fields that should be returned for the products in the group_products section.
If requested group product fields are missing from a product, that product won't appear in the group_products section.
StringNo
excludeVariantstrueExclude variants from the response. The default value is false. Valid values are 1, 0, true, false.BooleanNo
excludeViewDay30After how many days should viewed products be excluded.IntegerNo (Can be used only with userId)
excludeViewItem100How many viewed products should be excludedIntegerNo (Can be used only with userId)
excludePurchaseDay30After how many days should purchased products be excludedIntegerNo (Can be used only with userId)
excludePurchaseItem100How many purchased products should be excludedIntegerNo (Can be used only with userId)
hpfalseMakes affinities affect products of the response. The default is false.BooleanNo
dayLimit2If FMT is published_time, it adds a day limit filter. The default is 2.IntegerNo
productIdABC123CBACurrent product IDStringNo

Sample Request

The sample below displays a request to User Engagement, a personalized recommendation algorithm that analyzes the current user’s most recent interactions (such as product views, clicks, or cart actions) to deliver highly relevant product suggestions in real time.

GET https://recommendation.api.useinsider.com/v2/user-engagement?locale={locale}&userId={userId}&partnerName={partnerName}

Sample Response

{
    "success": true,
    "total": 10,
    "types": {
        "ue": 10
    },
    "data": [
        "649517_49890",
        "568334_49053",
        "639714_49677",
        "651579_3255",
        "614493_50094",
        "614508_49668",
        "568334_47380",
        "641331_49914",
        "621390_3255",
        "646581_48990"
    ]
}

Fallback Algorithms

If the current user has not visited two or more products, or if user engagement recommendations are filtered out, recommendations from the following algorithms are returned in sequence: