What inference can be made out of Baseline drift distance in data quality monitoring sagemaker?

You can find information on how the distributions are compared here (see distribution_constraints in the table):

https://docs.aws.amazon.com/sagemaker/latest/dg/model-monitor-byoc-constraints.html

You can change the threshold in the constraint file to what you would like.

The baseline computes baseline schema constraints and statistics for each feature using Deequ. If youwould like more details you can take a look at the implementation here:

https://github.com/awslabs/deequ/blob/master/src/main/scala/com/amazon/deequ/analyzers/Distance.scala