Creating and training solutions
Summarize
Summary of Creating and training solutions
ServiceNow’s Predictive Intelligence (PI) provides multiple machine learning frameworks that enable customers to create and train solutions for predicting, recommending, and organizing data outcomes. These solutions support automation and improved decision-making by leveraging historical data.
Show less
Customers manage and create these solutions via the Predictive Intelligence homepage in their ServiceNow instance. Each solution type addresses different prediction needs and can be invoked by any application through a prediction API.
Types of Solutions
- Classification solutions: Automatically categorize and route records during creation based on past data, improving workflow assignment and efficiency.
- Similarity solutions: Recommend resolutions by identifying similarities between new and existing records, aiding in quicker problem resolution.
- Clustering solutions: Group similar records to identify patterns and major incidents for better incident management and analysis.
- Regression solutions: (Legacy) Use numeric historical data to predict continuous values such as resolution times; note that creating new regression solutions is no longer supported from the Washington DC release onward, though existing regression solutions can still be edited and trained.
Selecting Data Records for Training
Effective training depends on quality data. Best practices include:
- Using input fields available at record creation to enable real-time predictions.
- Choosing output fields that are choice fields with a limited set of possible values for accuracy.
- Filtering out records with unreliable or incomplete output values to improve prediction quality.
- Including multiple examples for each output value and input field variation to ensure comprehensive model training.
Training Process and Data Security
Training involves exporting the solution definition and related records to a centralized training server within the same datacenter. After training completes, the solution is imported back into the instance and training data is deleted from the server.
Key security and compliance points:
- Each datacenter uses its own dedicated training server; data does not leave the datacenter.
- Prediction occurs on a centralized prediction server in the same datacenter with trained models cached for efficiency.
- All communications between the instance and training service are encrypted via HTTPS and occur within the datacenter firewall.
- Customers should verify their configuration meets compliance requirements.
Troubleshooting
For common issues related to solution training, customers should consult the Predictive Intelligence Common Issues article available in the Now Support Knowledge Base, which provides guidance on resolving typical problems.
Use one of the Predictive Intelligence (PI) frameworks to create and train machine-learning solutions. Each framework delivers a different solution type for training the system to predict, recommend, and organize data outcomes.
Types of solutions
The three PI frameworks provide different solutions that can be invoked by any application through a prediction API to make a prediction. Create and train your own solutions using your previous data. Navigate to to view and create solutions.
- Classification solutions:
Sets field values during record creation to automatically categorize and route work based on past records. See Create and train a classification solution.
- Similarity solutions:
Identifies similarities between new and existing records to recommend resolutions. See Create and train a similarity solution.
- Clustering solutions:
Groups similar records into clusters to identify patterns and major incidents. See Create and train a clustering solution.
- Regression solutions: Note:Uses historic data to predict numeric outputs, such as estimating the time it takes to resolve an incident or case. See Create and train a regression solution.From the Washington DC release, support for creating new regression solutions was removed. You can still edit and train existing regression solutions, but you won't be able to initiate new ones.
Selecting data records for training your solution
- The solution definition input fields are available to users when creating records. To make predictions at record creation, the solution must have the input field values at record creation.
- The solution definition output field is a choice field. To make more accurate predictions, limit the output field to a finite set of possible values.
- The training records only contain correct values for the output field. To make more accurate predictions, filter out any records that have unreliable output field values. For example, if recently closed incidents are subject to review and change for a month, filter out any recently closed incidents.
- The training records contain multiple examples of each output field value that you want the solution to predict. To provide more record coverage, include multiple examples of each output field value.
- The training records include common variations of the input fields. To provide more record coverage, include multiple examples of input field values.
Exporting your solution for training
To train a solution, you export its solution definition and associated records to a centralized training server within the same datacenter. When the training completes, the training server exports the solution back to your instance and deletes all of your training data from the server. Each datacenter has its own dedicated training server and the data doesn't leave the datacenter. Confirm that your configuration aligns with your compliance requirements.
Solution training troubleshooting
For troubleshooting common training issues, see the Predictive Intelligence Common issues [KB781893] article in the Now Support Knowledge Base.