---
title: Configure machine learning models
slug: '2118'
canonical_url: https://docs.coveo.com/en/2118/
collection: coveo-for-servicenow
source_format: adoc
---
# Configure machine learning models
This article explains how a ServiceNow instance administrator or developer who has access to the [Coveo organization](https://docs.coveo.com/en/185/) linked to their instance can configure [Coveo Machine Learning (Coveo ML)](https://docs.coveo.com/en/188/) [models](https://docs.coveo.com/en/1012/) in their [query pipelines](https://docs.coveo.com/en/180/) linked to Coveo for ServiceNow widgets.

## Configure Coveo ML models

The Coveo for ServiceNow widgets automatically log [Coveo Analytics events](https://docs.coveo.com/en/260/).
Once sufficient [data](https://docs.coveo.com/en/259/) has been gathered, this data can be leveraged by [Coveo Machine Learning](https://docs.coveo.com/en/1727/) models to provide highly relevant AI-powered recommendations.

You can create and then associate Coveo ML models to your query pipeline to ensure the most relevant content is always shown in your Coveo for ServiceNow widgets.

. On the Coveo Administration Console [**Models**](https://platform.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) ([platform-ca](https://platform-ca.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) | [platform-eu](https://platform-eu.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) | [platform-au](https://platform-au.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/)) page, [create](https://docs.coveo.com/en/1832/) an [Automatic Relevance Tuning (ART)](https://docs.coveo.com/en/1013/) model.

ART models use [Intelligent Term Detection (ITD)](https://docs.coveo.com/en/207/) to automatically refine [queries](https://docs.coveo.com/en/231/) with additional contextual information (for example, important keywords from a large textual case description).
They also ensure that [items](https://docs.coveo.com/en/210/) which are deemed highly relevant are included in the query result set and have a fairly high ranking score value, even if those items don't actually match the original query.

. [Associate](https://docs.coveo.com/en/l1ca1038/) the ART model with the desired [query pipeline](https://docs.coveo.com/en/3198/).
While doing so, on the **Associate a Model** subpage, under **Advanced Configuration**, check the **Comply with Intelligent Term Detection (ITD)** box.
. [Create](https://docs.coveo.com/en/3398/) a [Query Suggestion (QS)](https://docs.coveo.com/en/1015/) model.

QS models provide a list of relevant query completion suggestions as the end user is typing in a search box.
They can also make the [search-as-you-type](https://docs.coveo.com/en/2068/) feature more powerful and reliable.

. [Associate](https://docs.coveo.com/en/l1mf0321/) the QS model with the desired [query pipeline](https://docs.coveo.com/en/3198/).

Alternatively, you can [configure an A/B test](https://docs.coveo.com/en/3255/) to test your new query pipeline, which now contains your Coveo ML models, against the default, original query pipeline.

## What's next?

* You may want to learn how to generate usage analytics [reports](https://docs.coveo.com/en/266/) to help you identify possible content gaps, discover how your Coveo for ServiceNow widgets are being used by your customers and support agents, etc.
(see [Usage analytics reports](https://docs.coveo.com/en/1674/)).
* If you require additional specific usage analytics data, you should learn how to log custom usage analytics events through the [Coveo JavaScript Search Framework](https://docs.coveo.com/en/187/) (see [Send your own UA events](https://docs.coveo.com/en/365#send-your-own-ua-events)).