Skip to content

Recommend

Recommender solution primarily focuses on user needs and takes the recommended action to maximize user satisfaction and business growth. If you go through the following endpoints, you will know about different recommended endpoints and their purposes. You can use them based on your product and the target user in your application.

Item Recommend

Item recommend endpoint understands the content of your item and returns the most similar items as response. You can use this endpoint on product details page.

Request path:

POST /v1/item/recommend
Prerequisite parameter:

name key type value type description
user_id str str Represents the id of a logged-out unique user.
member_id Optional str Represents the id of a logged-in unique user.
item_id str str Represents the id of an item.
details bool bool If you want to get recommended items with details this parameter would be True otherwise it would be False.

Behavior Recommend

Behavior recommend endpoint understands user behavior such as browse, purchase, favorites, time spent in your application and returns the most suitable items for them as response. You can use this endpoint on user feed, top page, personalized suggestions etc.

Request path:

POST /v1/behavior/recommend

Prerequisite parameter:

name key type value type description
user_id str str Represents the id of a logged-out unique user.
member_id Optional str Represents the id of a logged-in unique user.
details bool bool If you want to get recommended items with details this parameter would be True otherwise it would be False.

Rank Recommend

Rank recommend endpoint considers all sorts of possible parameters in your application such as user behavior, item co-relation, external impact, business impact and returns the trending items for given interval as response. You can use it on user feed, top page, personalized suggestions etc.

Request path:

POST /v1/rank/recommend

Prerequisite parameter:

name key type value type description
top_n_item int int Represents number of top ranked items in given time interval.
interval Enum Selected enum value Represents the time range depending which it will predict trending and top recommended items. Available values are weekly, bi-weekly, monthly, quarterly, yearly. Interval should be similar to the interval parameter of ../rank/settings endpoint.
details bool bool If you want to get recommended items with details this parameter would be True otherwise it would be False.

Image Recommend

Image recommend endpoint understands the features of your input image and returns the most similar items in your catalog in terms of the image features. It also considers user behavior to boost the result. You can use this endpoint on product details page as well.

Request path:

POST /v1/image/recommend

Prerequisite parameter:

name key type value type description
user_id str str Represents the id of a logged-out unique user.
member_id Optional str Represents the id of a logged-in unique user.
item_id str str Represents the id of an item.
ItemDetails Optional[Dict[str, str]] str Represents the item details. If you use unknown item_id which does not exist in your data source then you have to pass item details to get most similar items.
image_url str str Represents the image url of an item from this url it generate features will find the most similar items.
price int int Represents the price of the given image_urls item.
category Optional[List[str]] int Represents the list of categories of the given image_urls item. This category values has to be matched with the previously added items data
details bool bool If you want to get recommended items with details this parameter would be True otherwise it would be False.

Search Recommend

This endpoint understands user behavior based on their search history and returns the most suitable items for them as response. You can use this endpoint on user feed, top page, personalized suggestions etc.

Request path:

POST /v1/search/recommend

Prerequisite parameter:

name key type value type description
user_id str str Represents the id of a logged-out unique user.
member_id Optional str Represents the id of a logged-in unique user.
details bool bool If you want to get recommended items with details this parameter would be True otherwise it would be False.