All Products
Search
Document Center

Artificial Intelligence Recommendation:Result details

Last Updated:Apr 01, 2026

When AIRec returns recommendations, the response contains a top-level structure with a request ID and a ranked list of result items. This page describes every field in that response, including the filtering algorithms mapped to MatchInfo values.

Response parameters

ParameterTypeDescription
RequestIdStringThe request ID.
ResultList\<Result Item\>The ranked list of recommended items. Each entry is a result item. Items are ordered by recommendation ranking.

Parameters of a result item

ParameterTypeDescription
TraceIdStringThe event tracking ID. Always ali. Upload this value with user behavior data on the recommended item.
ItemIdStringThe ID of the recommended item.
ItemTypeStringThe type of the recommended item.
MatchInfoStringThe filtering algorithm used to select the item. See MatchInfo values for the full mapping.
WeightintThe recommendation weight multiplier. 1 means no weight increase. A value greater than 1 means an increased weight is applied.
flowWeightdoubleThe traffic throttling adjustment applied to the recommendation weight. 0 means unaffected. A positive value means the weight is increased. A negative value means the weight is decreased.
PositionIntegerThe zero-indexed display position of the item. Results are sorted by this value. This parameter is informational and can be ignored.
TraceInfoStringThe event tracking string for algorithmic attribution. When a user behavior event (such as a click) occurs on a recommended item, upload this value together with the behavior data. The value varies per item.
messageStringA semicolon-delimited string with five fields that describe the recommendation reason. See message field structure below.

Using TraceId and TraceInfo for event tracking

TraceInfo is required for algorithmic attribution. When a user interacts with a recommended item — for example, by clicking it — upload TraceInfo along with the behavior data. Without this, AIRec cannot attribute user behavior back to the recommendation that triggered it, which degrades the quality of future recommendations.

TraceId is a fixed identifier with the value ali.

Message field structure

The message field is a string of five substrings separated by semicolons (;):

PositionContentNotes
1stThe MatchInfo value, or the matchType value from debug_resultIdentifies the filtering algorithm
2ndThe item ID and type of the recommended item that is filteredEmpty if the result was generated without historical behavior data
3rdThe timestamp when filtering was triggered, accurate to seconds0 if the result was generated without historical behavior data
4thA human-readable description of the recommendation reasonUse this for debugging why an item was recommended
5thThe timestamp in DateTime formatUse this for debugging

MatchInfo values

The MatchInfo field identifies which filtering algorithm selected the item. The following table maps each value to its algorithm.

MatchInfo valueFiltering algorithm
minorRecommendation based on positions
customCustom recommendation
hilpLoop exposure
hot_new, hot_full, hot_common, hot_mid, or pool_div_hot_commonRecommendation of best-selling items
search_fullRecommendation of supplementary items when personalized and best-selling items are insufficient
new_newRecommendation of new items
emb_item2vec_common, emb_tag2vec_common, or emb_title2vec_commonRecommendation of items 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_commonRecommendation based on collaborative filtering
u2x2i_u2category_common or u2x2i_u2category_newRecommendation for items of preferred categories
u2x2i_u2channel_common or u2x2i_u2channel_newRecommendation of content from preferred channels
u2x2i_u2author_common or u2x2i_u2author_newRecommendation of content that is created by preferred authors
u2x2i_u2shop_common or u2x2i_u2shop_newRecommendation of items from preferred stores
u2x2i_u2brand_common or u2x2i_u2brand_newRecommendation for items of preferred brands
u2x2i_u2tags_common or u2x2i_u2tags_newRecommendation of items with preferred tags
u2x2i_u2organization_common or u2x2i_u2organization_newRecommendation of items published by preferred organizations
u2x2i_umu2x_commonRecommendation based on Umeng information
u2x2i_nuu2x_common or u2x2i_u2vector_commonRecommendation based on user information