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
| Parameter | Sample Value | Description | Data Type | Required |
|---|---|---|---|---|
| partnerName | mybrand | Partner Identifier assigned by Insider. You can use PartnerID as well. | String | Yes |
| locale | us_US | Locale of requested product catalog | String | Yes |
| platform | web | Requested platform. Web comes by default. | Enum | No |
| userId | a1b2c3d4 | User identifier which is assigned by Insider | String | Yes |
| currency | USD | Requested currency of the products. If no value is set, the default currency in your settings is used. | String | Yes |
| size | 50 | Required number of items in response. Valid values are 0 to 100. | Integer | No |
| categoryList | [“Clothes”, “Skirts”] | Category filter of the products | Array (of string) | No |
| filter | Smart Recommender filtering. There can be more than one filter parameter. | String | No | |
| details | true | Adds details to the products of the response | Boolean | No |
| shuffle | false | Shuffles the products of the response | Boolean | No |
| getGroupProducts | false | Determines if the products within the same groupcode should be returned in the recommendation response | Boolean | No |
| 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. | String | No | |
| excludeVariants | true | Exclude variants from the response. The default value is false. Valid values are 1, 0, true, false. | Boolean | No |
| excludeViewDay | 30 | After how many days should viewed products be excluded. | Integer | No (Can be used only with userId) |
| excludeViewItem | 100 | How many viewed products should be excluded | Integer | No (Can be used only with userId) |
| excludePurchaseDay | 30 | After how many days should purchased products be excluded | Integer | No (Can be used only with userId) |
| excludePurchaseItem | 100 | How many purchased products should be excluded | Integer | No (Can be used only with userId) |
| hp | false | Makes affinities affect products of the response. The default is false. | Boolean | No |
| dayLimit | 2 | If FMT is published_time, it adds a day limit filter. The default is 2. | Integer | No |
| productId | ABC123CBA | Current product ID | String | No |
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: