{"revision":"c10276e953456835cdbb1f3a60d58ae1980be353","document":{"id":24351,"path":"intelligent-experiences/predictive-intelligence/predictive-intelligence.md","title":"Explore Predictive Intelligence","bundle":null,"doc_type":null,"release":"australia","body":"\n# Explore Predictive Intelligence\n\nServiceNow® Predictive Intelligence is a platform function that provides a layer of artificial intelligence that empowers features and capabilities across ServiceNow® applications to provide better work experiences.\n\n## Overview of Predictive Intelligence\n\nPredictive Intelligence is a powerful set of tools applying artificial intelligence and machine learning to make predictions. You can create and train models in three different frameworks: classification, clustering, and similarity. A trained solution can be invoked by any ServiceNow application through an API.\\[Omitted image \"predictive-intelligence-resolves-faster.png\"\\] Alt text: The benefits of using Predictive Intelligence.\n\nTo learn more about ways to use existing models, see [Using Predictive Intelligence](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/australia/markdown/australia/intelligent-experiences/predictive-intelligence/using-predictive-intelligence.md).\n\n## Predictive Intelligence for on-premise customers\n\nPredictive Intelligence is also available for on-premise customers. If you're interested in deploying this product on-premise, contact your account manager. For on-premise installation and configuration instructions, see the complete instructions for [Machine Learning Engine installation and configuration for self-hosted customers \\[KB0782052\\]](https://support.servicenow.com/kb?id=kb_article_view&sysparm_article=KB0782052) in the Now Support Self-Hosted Knowledge Base.\n\n**Note:** Only on-premise accounts can access the Now Support Self-Hosted Knowledge Base.\n\n## Terminology\n\n-   **Artificial intelligence**\n\n    Systems designed to do work that needs a level of human intelligence to accomplish.\n\n-   **Machine learning**\n\n    Ability for models to improve over time with more experience.\n\n-   **Models**\n\n    Collections of algorithms, math, and statistics that make predictions and decisions based on input-output data.\n\n-   **Training**\n\n    Adding or changing data that the model is based on to affect future predictions.\n\n-   **Supervised Training**\n\n    Providing input-out pairs so that the model can generate rules that connect the two.\n\n-   **Unsupervised Training**\n\n    Providing raw data so that the model can identify structures in the data set.\n\n-   **Training frequency**\n\n    How often models are retrained to incorporate new data into an existing model.\n\n-   **Word corpus**\n\n    Vocabulary that a model can use to look for textual similarity.\n\n\n## Predictive model components\n\nA predictive model includes these components, some of which you must provide.\n\n-   **Solution definition**\n\n    A data record you create and configure that specifies these values for training a predictive model.\n\n    -   The records used to train the model. For example, only train on incidents that are resolved or closed within the last six months.\n    -   The input fields that the model uses to make predictions. For example, use the incident short description to make a prediction.\n    -   The output field whose value the model predicts. For example, set the incident category based on the short description.\n    -   The frequency to retrain the model. For example, retrain the model every 30 days.\n-   **Solution**\n\n    The solution is the result of a solution definition that you've trained in a ServiceNow datacenter. Predictive Intelligence uses the solution to predict a target field value given one or more input field values. All solutions specify these values.\n\n    -   The solution precision is the aggregate percentage of correct predictions. For example, a precision of 50 means that out of 100 predictions, half of them should have the correct value.\n    -   The solution coverage is the aggregate percentage of records that receive a prediction. For example, a coverage of 50 means half of all eligible records actually receive a prediction.\n    -   The solution classes are the output field values for which the model can make predictions. Each class is an output field value with a list of possible precision, coverage, and distribution metrics to choose from. For example, the Incident Categorization solution has a class for each category such as software, inquiry, and database.\n    -   The class distribution is the percentage of records from the entire table that have this particular output field value. For example, a distribution of 50 for the inquiry class means that half of incidents have the inquiry category.\n\n-   **[Predictive Intelligence frameworks](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/australia/markdown/australia/intelligent-experiences/predictive-intelligence/predictive-intelligence-frameworks.md)**  \nPredictive Intelligence provides three different model frameworks in the Australia release: classification, similarity, and clustering. Each framework specializes in different types of predictions.\n-   **[ServiceNow apps and features that use Predictive Intelligence](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/australia/markdown/australia/intelligent-experiences/predictive-intelligence/servicenow-apps-features-use-predictive-intelligence.md)**  \nLearn about ServiceNow applications and features that leverage Predictive Intelligence. Solutions that you can adapt are available for various business units and industries.\n\n**Parent Topic:**[Predictive Intelligence](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/australia/markdown/australia/intelligent-experiences/predictive-intelligence/predictive-intelligence-landing.md)\n\n"}}