--- title: Automatic Relevance Tuning (ART) model card slug: pakd0065 canonical_url: https://docs.coveo.com/en/pakd0065/ collection: leverage-machine-learning source_format: adoc --- # Automatic Relevance Tuning (ART) model card ## What's a model card? A [model](https://docs.coveo.com/en/1012/) card is a document that provides a summary of key information about a [Coveo Machine Learning (Coveo ML)](https://docs.coveo.com/en/188/) [model](https://docs.coveo.com/en/1012/). It details the model's purpose, intended use, performance, and limitations. ## Model details The [Coveo Machine Learning (Coveo ML)](https://docs.coveo.com/en/188/) [Automatic Relevance Tuning (ART)](https://docs.coveo.com/en/1013/) model dynamically adjusts the ranking of search results based on end-user interactions and query behavior. The [ART](https://docs.coveo.com/en/1013/) model continuously learns from search analytics to optimize results relevance without requiring manual tuning. [ART](https://docs.coveo.com/en/1013/) leverages behavioral signals, including [queries](https://docs.coveo.com/en/231/) and clicks, to elevate search results that have previously demonstrated strong user engagement and satisfaction for similar [queries](https://docs.coveo.com/en/231/). * **Development team**: Coveo ML team * **Initial release date**: 2015. Major changes can occur and are communicated via Coveo release notes. * **Activation**: The [ART](https://docs.coveo.com/en/1013/) model is created and assigned to query pipelines using the [Coveo Administration Console](https://docs.coveo.com/en/183/). ## Intended use * **Intended purpose**: To enhance the end-user's search experience by automatically boosting search results based on historical engagement patterns for similar [queries](https://docs.coveo.com/en/231/). * **Intended input**: The end user's search [query](https://docs.coveo.com/en/231/) and context. * **Intended output**: A ranked list of top items (typically between 5 to 50) with corresponding ranking score boosts for the current [query](https://docs.coveo.com/en/231/). These boosts are passed to the [index](https://docs.coveo.com/en/204/) and applied in the final [ranking function](https://docs.coveo.com/en/237/). * **Intended users**: End users of Coveo customers. ## Factors The ART model enhances search relevance by leveraging aggregated analytics data collected on behalf of each customer. It considers search [queries](https://docs.coveo.com/en/231/) and clicked results, as well as contextual factors in which these interactions occurred. The model is trained to optimize the search result ranking for each query. A distinct model is trained for each supported language. By default, ART also records the [search interface](https://docs.coveo.com/en/2741/) in which the query is performed, which allows for query-time filtering based on the search interface. ## Training data The data used to train each customer's ART model is derived from that customer's end-user interactions with Coveo's platform. It includes the following: * Events received via API calls, such as [query](https://docs.coveo.com/en/231/) information, [client ID](https://docs.coveo.com/en/lbjf0131/), [user ID](https://docs.coveo.com/en/268/), and clicks. * Data automatically collected by Coveo's platform, such as the user agent, IP address, or any information derived from the IP address like country or city. * Optional custom context information provided by customers to enrich the search context, such as the specific page, specific [search hub](https://docs.coveo.com/en/1342/), or specific user segment. * In [Coveo for Commerce](https://docs.coveo.com/en/ladb6157/) implementations, ART can also learn from commerce-specific user actions such as cart and purchase events. All data collection and processing are performed on behalf of each customer, in compliance with Coveo's privacy and security commitments. ## Performance The quality and performance of the ART model can be assessed by looking at the search performance [metrics](https://docs.coveo.com/en/2041/) like clickthrough rate and average click rank, which typically improve as ART learns from historical interactions. Customers can also fine-tune the ART model's performance by adjusting the training dataset, and retraining frequency. You can use the [Relevance Inspector](https://docs.coveo.com/en/mbad0273/) to identify and validate search results promoted by ART. ## Limitations Certain conditions may reduce the effectiveness of the ART model: * **Data volume**: The effectiveness of the ART model relies on the volume of historical analytics data. As a result, new queries or low-traffic queries may yield less accurate results. A query needs to have occurred multiple times for ART to learn which search results should be boosted. * **Feedback type**: The ART model doesn't directly consider explicit end-user feedback, such as thumbs up and thumbs down. ## Best practices Best practices for the [ART](https://docs.coveo.com/en/1013/) [model](https://docs.coveo.com/en/1012/) are documented [here](https://docs.coveo.com/en/l1ca1038/). All usage must comply with Coveo's [Acceptable Use Policy](https://www.coveo.com/en/company/legal/terms-and-agreements/acceptable-use-policy).