Explore Predictive Intelligence
Summarize
Summary of Explore Predictive Intelligence
ServiceNow® Predictive Intelligence is a robust platform function that enhances user experiences by leveraging artificial intelligence and machine learning across various ServiceNow applications. It allows users to create and train predictive models that can be integrated with other ServiceNow products to optimize workflows.
Show less
Key Features
- Model Creation and Training: Users can develop models using input-output data, facilitating predictions and decisions.
- Training Types: Supervised training uses labeled data, while unsupervised training analyzes raw data for patterns.
- Predictive Model Components: Includes solution definitions, input/output fields, retraining frequency, and word corpus.
- Solution Precision and Coverage: Precision indicates the accuracy of predictions, while coverage refers to the percentage of records receiving predictions.
- Frameworks: Three distinct frameworks are available, enabling predictions, recommendations, and data organization through API calls.
Key Outcomes
By utilizing Predictive Intelligence, ServiceNow customers can enhance decision-making through accurate predictions and improved work experiences. The solution's ability to retrain models and adapt to new data ensures that organizations can maintain relevant and effective outcomes in their operations.
ServiceNow® 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.
Overview of Predictive Intelligence
Predictive Intelligence is a powerful set of tools to use artificial intelligence and machine learning to improve the work experience. You can create and train models on the platform and integrate with other ServiceNow products and applications.
The following introduces the underlying concepts behind Predictive Intelligence and the different frameworks available.
To learn more about ways to use existing models, see Using Predictive Intelligence.
Predictive Intelligence for on-premise customers
Terminology
- Artificial intelligence
- Systems designed to do work that needs a level of human intelligence to accomplish.
- Machine learning
- Ability for models to improve over time with more experience.
- Models
- Collections of algorithms, math, and statistics that make predictions and decisions based on input-output data.
- Training
- Adding or changing data that the model is based on to affect future predictions.
- Supervised Training
- Providing input-out pairs so that the model can generate rules that connect the two.
- Unsupervised Training
- Providing raw data so that the model can identify structures in the data set.
- Training frequency
- How often models are retrained to combine the existing model with new training data.
- Word corpus
- Vocabulary that a model can use to look for textual similarity.
Predictive model components
- Solution definition
- A data record you create and configure that specifies these values for training a predictive model.
- The records used to train the model. For example, only train on incidents that are resolved or closed within the last six months.
- The input fields that the model uses to make predictions. For example, use the incident short description to make a prediction.
- The output field whose value the model predicts. For example, set the incident category based on the short description.
- The frequency to retrain the model. For example, retrain the model every 30 days.
- Solution
- 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.
- 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.
- 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.
- 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.
- 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.
Predictive Intelligence frameworks
Predictive Intelligence provides three frameworks in the Washington DC release. Each framework has different solution types to train the system to predict, recommend, and organize data outcomes. A trained solution can be invoked by any application through an API to make a prediction. More information can be found in Predictive Intelligence frameworks.