Managing the Coveo Machine Learning Model Associations With Query Pipelines

Once a Coveo Machine Learning (Coveo ML) model has been created (see Adding and Managing Coveo Machine Learning Models), it must be associated with a query pipeline in order to be effective in a search interface.

Organizationmembers with the required privileges can access the Machine Learning tab of a query pipeline configuration page to manage Coveo ML model associations for that query pipeline (see Coveo Machine Learning Models).

Leading Practices

Duplicate the Production Query Pipeline

  1. Once you have created a Coveo ML model, the leading practice is to duplicate the query pipeline with which you plan to associate the model, and then associate the model with the pipeline copy.

  2. Once satisfied with the model efficiency on the pipeline copy, dissociate the model from the test pipeline and associate it with the production pipeline. You can test your Coveo ML models efficiency by performing A/B tests or model testings.

  3. Delete the test pipeline.

Validate That the Model Is Effective

To validate that your Coveo ML models work as expected, you can inspect your models.

Plan the Usage of Custom Contexts to Improve the Model Relevance

While the various Coveo ML features can perform well without custom context information, using custom contexts can take Coveo ML relevance one step further.

You can define custom contexts and then pass appropriate ones along with usage analytics events and queries to allow Coveo ML to take them into account.

If you’re just starting using Coveo ML in your solution, you can skip this step to take advantage of Coveo ML features more quickly and easily, and consider using custom contexts in a second phase.

Access the “Machine Learning” Tab of a Query Pipeline

You must first access the Machine Learning tab of the query pipeline that you want to edit to manage its model associations.

  1. On the Query Pipelines page, click the desired query pipeline, and then in the Action bar, click Edit.

  2. On the query pipeline subpage, ensure the Machine Learning tab is selected.

Associate a Model With a Query Pipeline

The process of associating a Coveo ML model with a query pipeline differs depending on the Coveo ML feature you want to associate. Click one of the following model links to access the corresponding procedure:

Associate Automatic Relevance Tuning (ART) Models

2816-ARTModelAssociation

  1. Access the Machine Learning tab of the query pipeline with which you want to associate a Coveo ML model.

  2. In the Machine Learning tab, click Associate model.

  3. In the Associate a Machine Learning Model dialog that appears:

    • In the Model drop-down menu, select the desired model.

    • (Optional) In the Select a condition drop-down menu, select a condition if you want the model to apply only when certain circumstances are satisfied. You can also create a condition.

  4. (Optional) Tune the parameters in the Advanced Configuration section.

  5. Click Associate Model.

Associate Query Suggestion (QS) Models

2816-QSModelAssociation

  1. Access the Machine Learning tab of the query pipeline with which you want to associate a Coveo ML model.

  2. In the Machine Learning tab, click Associate model.

  3. In the Associate a Machine Learning Model dialog that appears:

    • In the Model drop-down menu, select the desired model.

    • (Optional) In the Select a condition drop-down menu, select a condition if you want the model to apply only when certain circumstances are satisfied. You can also create a condition.

  4. Click Associate Model.

Associate Event Recommendation (ER) Models

2816-ERModelAssociation

  1. Access the Machine Learning tab of the query pipeline with which you want to associate a Coveo ML model.

  2. In the Machine Learning tab, click Associate model.

  3. In the Associate a Machine Learning Model dialog that appears:

    • In the Model drop-down menu, select the desired model.

    • (Optional) In the Select a condition drop-down menu, select a condition if you want the model to apply only when certain circumstances are satisfied. You can also create a condition.

      Associate all ER models with the same pipeline and assign each ER model its own condition.

  4. Click Associate Model.

    Now that your ER model is associated with a pipeline, you must include a Coveo JavaScript Search Recommendation component in your website pages where you want to show recommendations from this model (see Coveo Machine Learning Event Recommendations Deployment Overview).

Associate Dynamic Navigation Experience (DNE) Models

2816-DNEModelAssociation

  1. Access the Machine Learning tab of the query pipeline with which you want to associate a Coveo ML model.

  2. In the Machine Learning tab, click Associate model.

  3. In the Associate a Machine Learning Model dialog that appears:

    • In the Model drop-down menu, select the desired model.

    • (Optional) In the Select a condition drop-down menu, select a condition if you want the model to apply only when certain circumstances are satisfied. You can also create a condition.

  4. (Optional) Tune the parameters in the Advanced Configuration section.

  5. Click Associate Model.

    Now that your DNE model is associated with a pipeline, you must configure dynamic facets in order to take advantage of your model in your search interface.

Associate Product Recommendations (PR) Models

UPCOMING

2816-PRModelAssociation

  1. Access the Machine Learning tab of the query pipeline with which you want to associate a Coveo ML model.

  2. In the Machine Learning tab, click Associate model.

  3. In the Associate a Machine Learning Model dialog that appears:

    • In the Model drop-down menu, select the desired model.

    • (Optional) In the Select a condition drop-down menu, select a condition if you want the model to apply only when certain circumstances are satisfied. You can also create a condition.

  4. Select the appropriate Strategy in the Advanced Configuration section.

  5. Click Associate Model.

Edit a Model Association

  1. In the Machine Learning tab of the desired query pipeline, click the desired model association, and then in the Action bar, click Edit.

  2. (Optional) On the Edit a Model Association subpage, under Associated model, click Open Model to review the model information or edit its configuration.

  3. While on the Edit a Model Association subpage, you can also edit the available parameters (see ART Advanced Configuration Options or DNE Advanced Configuration Options).

  4. Click Save.

Advanced users may want to edit a model association with JSON.

Dissociate a Model

  1. In the Machine Learning tab of the desired query pipeline, click the model that you want to dissociate from this pipeline.

  2. In the Action bar, click Dissociate.

Reorder Model Associations

The Coveo ML models of a given type are executed in the order in which they appear in the page until a condition is satisfied.

The first model on the list will be used if no conditions are met.

To reorder model associations in a query pipeline

  1. In the Machine Learning tab of the desired query pipeline, click the model whose position you want to change.

  2. In the Action bar, use the Move up or Move down arrows to change the position of the model.

ART Advanced Configuration Options

Ranking Modifier

The Recommended value of 250 typically modifies the ranking score of the ART results so that they appear among the top 10 search results.

You should only consider reducing the default value when ART result ranking scores significantly exceed the default ranking, such as when ART results are always appearing among the top five results. You generally don’t want ART results to completely override the normal search results ranking, but rather bring them among the first top 10 results. Typical ranking modifiers are between 50 and 250.

Oppositely, you should only consider increasing the default value when the ART results generally don’t appear within the first search result page. Increase the value until the ART results surface among the top 10 results.

ART results can be buried lower in search results when other query pipeline rules such as Featured Results and Ranking Expressions, or hard-coded query ranking expressions (QREs) significantly modify result ranking scores. When this is the case, reevaluate and consider eliminating such query pipeline rules or hard-coded expressions.

Match the Advanced Query

The Match the advanced query check box is selected by default because it’s typically desirable for ART results to match search interface scope, facet selections, and filters. Items recommended by ART are typically not distinguishable from other results in search interfaces. If ART is allowed to inject results outside of the expected scope, the overall search experience may feel confusing for your users.

On a community search page, an end user selects the Knowledge Base Article value in the Item Type facet, enters acme television set in the search box, and then submits the query.

In the query pipeline, the query is processed by an ART model whose Match the advanced query option is enabled. Consequently, the model can only recommend knowledge base articles (i.e., items whose @documenttype field value is equal to kbarticle).

If the option was disabled, the model could also recommend items of a different type, such as videos and user manuals. However, the end user likely expects such items to be filtered out, resulting in a confusing experience.

You should only consider clearing the Match the advanced query check box for rare cases, when instructed to do so by Coveo Support.

Match the Query

The Match the query check box is cleared by default because it’s typically desirable for ART to be allowed to inject search results that don’t necessarily match the keywords entered in the search box by the end user.

Many customers on a community search page start seeking help on a popular product by entering the part number. However, many useful items available about this product don’t include that part number. Consequently, the initial search results don’t return relevant items, but customers keep adapting their keywords or navigating in search results until they find an appropriate result for the product.

Because ART learns that this result was useful in relation with this part number, when the Match the query check box is cleared, ART can now recommend it immediately, even if the result doesn’t match the part number.

Consider selecting the Match the query check box only if the negative side of ART appears to be more important than the benefits or when instructed to do so by Coveo Support.

Comply with Intelligent Term Detection (ITD)

Select the Enable Intelligent Term Detection (ITD) check box when you want large query expressions (essentially support case descriptions) to be processed by ART to refine the query before it’s sent to the index.

This option is particularly useful when the Coveo ML model is used in case deflection panels that may include long case descriptions in their queries.

When ITD is enabled, ART selects and injects the most relevant keywords from the large query expression into the current basic query expression (q). By default, this selection is based on the average importance of each term, and on the longest substring from your search interface user queries that’s part of a list of top user queries. The list contains the top user queries that have been submitted at least five times each in your search interface (see How Does Intelligent Term Detection (ITD) Work?).

DNE Advanced Configuration Options

Facet Ordering

The Facet ordering check box is selected by default because it’s typically desirable for DNE models to display the most relevant facets first. You can however deselect this check box if you want to take advantage of the other DNE model options, without having your facets automatically ranked.

Facet Value Ordering

The Facet Value Ordering check box is selected by default because it’s typically desirable for DNE models to display the most relevant facet values within a given facet first. You can however deselect this check box if you want to take advantage of the other DNE model options, without having your facet values automatically ranked.

Ranking Boost

The Ranking boost check box is selected by default because it’s typically desirable for DNE models to boost items that match facet values determined as relevant by the model. You can however:

  • Deselect this check box if you want to take advantage of the other DNE model options, without having search results that correspond to relevant facets boosted.

  • Adjust the default (recommended) boosting value applied to items matching relevant facet values.

    Increasing the ranking modifier above the recommended value can considerably alter your search results.

PR Strategies Options

UPCOMING

Only one strategy can be associated per pipeline. In other words, if you want to simultaneously leverage different strategies in your implementation, you must create three different pipelines, each dedicated to only one of these strategies.

For more information on Coveo ML PR and its strategies, see Product Recommendations Feature.

Interest-Based Recommender

When selecting this option, the model bases its product suggestions on actions previously made by the current user and others that share similar interests.

Frequently Bought Together

When selecting this option, the model recommends items related to the current product, based on products often bought together in the same shopping cart.

Frequently Viewed Together

When selecting this option, the model suggests items related to each of the current products, based on other products that are often viewed together in the same shopping session.

Cart Recommender

When selecting this option, the model recommends products that are complementary to the products in the user’s current shopping cart.

When selecting this strategy, the model recommends the most viewed products.

When selecting this strategy, the model recommends the most bought products.

Required Privileges

By default, members of the Administrators and Relevance Managers built-in groups can view and edit elements of the Query Pipelines page.

The following table indicates the privileges required to view or edit elements of the Query Pipelines page and associated panels (see Privilege Management and Privilege Reference).

Action Service - Domain Required access level
View model associations

Search - Query pipelines

Machine Learning - Models

View
Edit model associations

Search - Query pipelines

Machine Learning - Models

Edit
Recommended Articles