Predictive intelligence data limit

[Sanjh]

ServiceNow recommends that you have at least 30,000 to 300,000 data. What if we have less than that for predictive intelligence module.

[olgaredkina]

If you have less than 30,000 records the prediction/classification model might be less accurate. The lowest limit is 10,000, so if you have between 10,000 and 30,000 records, you can still try to create model. It would be better to spend more time on testing the model after training to assure it is providing the level of accuracy you are happy with

[Pranesh072 · Accepted solution]

The recommended number of records for training a good solution is from 30,000 through 300,000.

If you submit less records than the recommended minimum then solution may not cover all the scenarios which may leads to bad/less accurate predictions.

If you submit more than 300,000 records, the most recent 300,000 records are used to train the solution. Use only authentic records from the database.

Also depending upon the model, Servicenow sets minimum and maximum limit of records needed for training for every model definition.

• Similarity 10 - 100000
• Clustering 100 - 100000
• Classification 10000 - 300000
• Regression 10000 - 300000

These limits are controlled by the system properties - https://[instance].service-now.com/sys_properties_list.do?sysparm_query=nameSTARTSWITHglide.platform_ml.api.max%5EORnameSTARTSWITHglide.platform_ml.api.min&sysparm_view=

So it is recommended to have a training set with required and quality records so that it can cover most of different scenarios which will help in generation of high precession model.

[Lisha ramya C]

I am not able to create a new classification in predictive intelligence application. 

I got a two errors

Solution training requires a minimum number of 10000 records.

invalid insert

please help me