Category prediction uses a trained model to match a search query to a product category, then ranks results from that category higher. For example, a query like "running shoes" maps to "Sports > Footwear," surfacing athletic shoes above unrelated results. A query like "denim" maps to "Clothing > Pants," ranking jeans above denim-themed home goods.
To enable category prediction, complete three configurations: create and train a model, configure a query analysis rule that references the model, and add a sort expression that calls category_score.
Prerequisites
Before you begin, make sure that you have:
Category ID, commodity title, and category name fields configured as attribute fields in your application schema
(If using Commodity Data) Document data that contains category ID, commodity title, and category name fields
(If using Behavior Data) Click behavior data collected via data collection
Create and train a category prediction model
In the left-side navigation pane, choose Search Algorithm Center > Sort Configuration. In the navigation tree, click Category Prediction Model, then click Create.
On the Create Category Prediction page, fill in the model details.
Field Description Required Model name A name for the model Yes Data Type Commodity Data: document data from your application. Requires category ID, commodity title, and category name fields. Behavior Data: collected click behavior data. Yes Category ID The field representing the category ID in your application documents. Supports the INT data type. Must be a positive integer—a non-positive value causes a server error. Yes Commodity Title The field representing the commodity title. Supports TEXT and LITERAL data types. Yes Category Name The field representing the category name. Supports TEXT and LITERAL data types. Yes Filter Condition A condition to filter training data. Field names must match those in the application schema. Supports: <,>,<=,>=,=,!=. Separate multiple conditions with commas (,)—all conditions use AND logic. OR logic is not supported. Example:is_onsale > 0No 
Click Completed to go to the model details page.
On the Category Prediction Model page, the model status is Pending Training. Click Train in the Actions column to start training.
The model moves through the following states:
State Meaning Pending Training Model created, training not started Training Model is being trained Training Failed Training failed due to a data error Not Applied Training complete, not yet referenced for retrieval or sorting Trained and Not Passed Training complete, but the model failed to pass the training If you have questions, submit a ticket.
Configure query analysis and sort expressions
Create a query analysis rule
In the left-side navigation pane, choose Search Algorithm Center > Retrieval Configuration. In the navigation tree, click Query Analysis Rule Configuration, then click Create.
Configure the query analysis rule and save it.
Apply the model to rough sorting
Rough sorting is the first round of ranking.
In the left-side navigation pane, choose Search Algorithm Center > Sort Configuration. On the Policy Management page, click Create.
On the Create Policy page, enter a policy name. Set Scope to Rough Sort and Type to Expression. Only expressions are supported in the console. Custom plug-ins will be supported later.
In the Sort Configuration step, select
category_score()from the Scoring Characteristics drop-down list.Select a field, set the weight, and save the configuration.
Apply the model to fine sorting
Fine sorting is the second round of ranking.
On the Create Policy page, enter a policy name. Set Scope to Fine Sort and Type to Expression. Only expressions are supported in the console. Custom plug-ins will be supported later.
In the Sort Configuration step, select
category_score(cate_id_field)from the Built-in Functions drop-down list.Replace
cate_id_fieldwith the category ID of your model and save the configuration.Verify the model status after it is referenced by the sort policy.
Run a search test on the application. Set the
raw_queryparameter to a search query to test the category prediction results.
Activate category prediction in API and SDK calls
Category prediction sorts search results only when the raw_query parameter is present and its value matches the search query in the index.
Set raw_query to the search query entered by the user:
raw_query=<search_query>When calling via API: URL-encode the value using
URL_ENCODE.When calling via SDK: no encoding needed.
When category prediction takes effect
The table below shows when category prediction applies, based on the index configuration and raw_query value.
| Index configuration | raw_query in request |
raw_query equals search query |
Category prediction applies? |
|---|---|---|---|
| Disabled | Yes | — | No |
| Disabled | No | — | No |
| Enabled | No | — | No |
| Enabled | Yes | No | No |
| Enabled | Yes | Yes | Yes |
Multi-index behavior: If a request covers multiple indexes, category prediction applies per-index based on the rules above.
# index3 prediction takes effect (query matches raw_query for index3 only)
query=index2:'index_query' AND index3:'search_query'&raw_query=search_query
# index2 prediction takes effect preferentially;
# if index2 config doesn't apply, index3 takes effect
query=index2:'search_query' AND index3:'search_query'&raw_query=search_queryLimits
Up to five category prediction models can be created per application.
The data fields used to train the model must be included in the indexes to which the query analysis rule is applied.
Before creating a model, configure category ID and related fields as attribute fields.
If a query analysis rule references a category prediction model and the request contains the
category_predictionparameter, an error occurs.For category prediction to take effect, all three of the following must be configured: a query analysis rule referencing the model, a sort expression containing the
category_scorefunction, and theraw_queryparameter in the request.Related API operations: Algorithms
Advanced usage
Combine with Named Entity Recognition (NER)
If you configure NER alongside category prediction in a query analysis rule, more documents are retrieved. The NER results are also used for retrieval. If no documents match the predicted categories, words in the search query are selectively ignored to broaden results—these broader results become the final category prediction output. For more information, see Named entity recognition.
Intervene in prediction results
Intervention lets you override the trained model's predictions, similar to query analysis intervention. For more information, see Intervention dictionaries for category prediction.