SageMaker Model Explainability Job Definition

An AWS SageMaker Model Explainability Job Definition is a resource that specifies the configuration for running explainability jobs on machine learning models. It defines how to generate insights into model predictions, such as feature importance or bias detection, using preconfigured tools. This job definition includes details like the model to analyze, input datasets, output locations, and compute resources. It allows you to consistently run explainability analyses on models to improve transparency, compliance, and trust in machine learning outcomes.

aws.sagemaker_model_explainability_job_definition

Fields

TitleIDTypeData TypeDescription
_keycorestring
account_idcorestring
creation_timecoretimestampThe time at which the model explainability job was created.
job_definition_arncorestringThe Amazon Resource Name (ARN) of the model explainability job.
job_definition_namecorestringThe name of the explainability job definition. The name must be unique within an Amazon Web Services Region in the Amazon Web Services account.
job_resourcescorejsonIdentifies the resources to deploy for a monitoring job.
model_explainability_app_specificationcorejsonConfigures the model explainability job to run a specified Docker container image.
model_explainability_baseline_configcorejsonThe baseline configuration for a model explainability job.
model_explainability_job_inputcorejsonInputs for the model explainability job.
model_explainability_job_output_configcorejsonThe output configuration for monitoring jobs.
network_configcorejsonNetworking options for a model explainability job.
role_arncorestringThe Amazon Resource Name (ARN) of the IAM role that has read permission to the input data location and write permission to the output data location in Amazon S3.
stopping_conditioncorejsonA time limit for how long the monitoring job is allowed to run before stopping.
tagscorehstore