Predictive Intelligence FAQ

[Bhanu Kiran]

1. Where are the training servers located?

Training servers are available in each data center. Predictor servers are also located in each data center.

2. Which types of fields (reference, list, etc.,) can be used as inputs for training?

The system will allow you to select any field available on the table. However, ServiceNow recommends using choice, string, or reference fields.

3. For classification solutions, which types of fields can be used as outputs? 
Similar to inputs, you can select any field available on the table. However, ServiceNow recommends using a string or a choice field with a finite set of possible values.

4. Is Predictive Intelligence available on tables other than Incident? 
Yes, Predictive Intelligence can be expanded to other tables outside of Incident, Case, HR Cases, and Event Management.

5. How many records are needed to train a viable solution?
The recommended number of records for training a good solution is from 30,000 through 300,000. If you submit more than 300,000 records, the most recent 300,000 records are used to train the solution.

6. For classification solutions, how many possible outputs can a single solution include?
A solution can only have 1 output.

7. Does Predictive Intelligence support multiple languages?
Language support is included for classification solutions but is limited to English for Similarity Solutions at this time. Please see the language field on the classification solution definition for more details.

8. Does Predictive Intelligence support encryption?
Yes, if your data is encrypted by Full disk encryption. If the field that you are using for training is encrypted using platform encryption, the sharedservice.worker user needs to use the correct encryption context role. Agent Intelligence is not supported if you are using Edge Encryption.

9. Who can use Agent/Predictive Intelligence? 
Agent/Predictive Intelligence was not available for on-prem customers or customers who have data sovereignty requirements. But starting from Orlando, it is available for on-prem customers as well.

If you're interested in deploying this product on-premise, please contact your account manager. For on-premise installation and configuration instructions, see Knowledge Base article KB0782052.

10. How do you preserve solutions during a system clone?
There is a system property that can be set to true in order to preserve your solutions. Note, this is available in the London release.

11. Can classes be excluded from prediction?
Yes.Under the Class Confidence record (you want to exclude), select the Precision Coverage Lookup combination record where Precision = 100 and Coverage = 0 and select Apply Values from the Actions list. Note, this applies only to classification solutions.

12. For classification solutions, what is the maximum number of prediction classes that a solution can support?

There is no fixed limit.

13. When a solution definition is scheduled to train on an interval, does the new solution automatically go live when the results are returned?
Yes, older versions are set to inactive. Administrators have the ability to activate an older version.

14. What is the difference between Agent Intelligence and Predictive Intelligence?

Nothing. Agent Intelligence was re-named to Predictive Intelligence from New York release.

15. What are some common mistakes when creating solution definitions?

The incorrect table is selected, dates are hardcoded in the filter or filter is erroneous, there are not enough rows to train the solution, and the wrong input fields have been selected.

Service Now published KB - KB0781894

[kim_kari]

Hi @Bhanu Kiran and everyone! Regarding sending records to the training servers, what data is included? The full records or only contents of the fields selected in the solution definition?

I have not found an explicit confirmation to this from the docs (example), Community, KB articles, or such.

EDIT: I got the below reply from Now Support in case someone else wonders the same thing:

"The full record is sent to the ML Trainer, incl. data fields not used as Input fields"

[tidert_24]

Hello @Bhanu Kiran 
Is it the same with now assist that i deducts the number of assists available? How is this licensing priced?