All Products
Search
Document Center

Artificial Intelligence Recommendation:Details of recommendation results

Last Updated:Sep 18, 2023

Response parameters

Parameter

Type

Description

Request Id

String

The request ID.

Result

List<Result Item>

The returned recommendation results. Each record corresponds to a recommended result item. The returned results are ranked by the order of recommendations.

Parameters of a result item

Parameter

Type

Description

TraceId

String

The event tracking ID. This parameter is uploaded together with user behavior on the recommended item. In this case, the value of this parameter is ali.

ItemId

String

The ID of the recommended item.

ItemType

String

The type of the recommended item.

MatchInfo

String

The algorithm used for filtering the item.

Weight

int

Indicates whether an increased weight is allocated to the recommended item. Value 1 indicates that the weight allocated to the recommended item is not increased. A value greater than 1 indicates that an increased weight is allocated to the recommended item.

flowWeight

double

Indicates whether the recommendation weight of the item is affected by traffic throttling. Value 0 indicates that the recommendation weight is not affected by traffic throttling. A value greater than 0 indicates that the recommendation weight is increased. A value less than 0 indicates that the recommendation weight is decreased.

Position

Integer

The position at which the recommended item is displayed. The position number starts from 0. The returned results are ranked by position. You can ignore this parameter.

TraceInfo

String

The information about event tracking. This parameter is used for algorithmic attribution. If behavior data such as a click is generated based on the recommended item, the value of this parameter must be uploaded together with the behavior data. The value of this parameter varies based on items.

message

String

The information about the recommendation reason. The value of this parameter is a string in which five substrings are separated by semicolons (;).

The first substring is the value of the MatchInfo parameter or the matchType parameter returned in debug_result.

The second substring displays the item ID and type of the recommended item that is filtered. This substring is empty if some of the recommendation results are provided without using historical behavior.

The third substring is the timestamp when the filtering is triggered. The timestamp is accurate to seconds. Value 0 is returned for this substring if some of the recommendation results are provided without using historical behavior.

The fourth substring is a message that describes the recommendation reason.

The last substring displays the timestamp in the DateTime format. This substring is used for debugging.

The following table describes the mapping relationships between values of the MatchInfo parameter and filtering algorithms.

Value

Filtering algorithm

minor

Recommendation based on positions

custom

Custom recommendation

hilp

Loop exposure

hot_new, hot_full, hot_common, hot_mid, or pool_div_hot_common

Recommendation of best-selling items

search_full

Recommendation of supplementary items when personalized and best-selling items are insufficient

new_new

Recommendation of new items

emb_item2vec_common, emb_tag2vec_common, or emb_title2vec_common

Recommendation of items that are similar to those on which user behavior has recently occurred

i2i_scategory_common, i2i_common_common, i2i_channel_common, i2i_swing_common, i2i_pcategory_common, i2i_u2scategory_common, or i2i_u2pcategory_common

Recommendation based on collaborative filtering

u2x2i_u2category_common or u2x2i_u2category_new

Recommendation for items of preferred categories

u2x2i_u2channel_common or u2x2i_u2channel_new

Recommendation of content from preferred channels

u2x2i_u2author_common or u2x2i_u2author_new

Recommendation of content that is created by preferred authors

u2x2i_u2shop_common or u2x2i_u2shop_new

Recommendation of items from preferred stores

u2x2i_u2brand_common or u2x2i_u2brand_new

Recommendation for items of preferred brands

u2x2i_u2tags_common or u2x2i_u2tags_new

Recommendation of items with preferred tags

u2x2i_u2organization_common or u2x2i_u2organization_new

Recommendation of items that are published by preferred organizations

u2x2i_umu2x_common

Recommendation based on Umeng information

u2x2i_nuu2x_common or u2x2i_u2vector_common

Recommendation based on user information