Model Deployment Monitoring Job

Docs > DDSQL Reference > Data Directory > Model Deployment Monitoring Job

A Model Deployment Monitoring Job in GCP is a managed process that continuously tracks the performance of deployed machine learning models. It monitors prediction data for issues such as data drift, feature skew, and model degradation. The job helps ensure model reliability by generating alerts and reports when anomalies are detected, allowing teams to maintain model accuracy and compliance over time.

gcp.aiplatform_model_deployment_monitoring_job

Fields

ID	Type	Data Type	Description
_key	core	string
analysis_instance_schema_uri	core	string	YAML schema file uri describing the format of a single instance that you want Tensorflow Data Validation (TFDV) to analyze. If this field is empty, all the feature data types are inferred from predict_instance_schema_uri, meaning that TFDV will use the data in the exact format(data type) as prediction request/response. If there are any data type differences between predict instance and TFDV instance, this field can be used to override the schema. For models trained with Vertex AI, this field must be set as all the fields in predict instance formatted as string.
ancestors	core	array<string>
bigquery_tables	core	json	Output only. The created bigquery tables for the job under customer project. Customer could do their own query & analysis. There could be 4 log tables in maximum: 1. Training data logging predict request/response 2. Serving data logging predict request/response
create_time	core	timestamp	Output only. Timestamp when this ModelDeploymentMonitoringJob was created.
datadog_display_name	core	string
enable_monitoring_pipeline_logs	core	bool	If true, the scheduled monitoring pipeline logs are sent to Google Cloud Logging, including pipeline status and anomalies detected. Please note the logs incur cost, which are subject to [Cloud Logging pricing](https://cloud.google.com/logging#pricing).
encryption_spec	core	json	Customer-managed encryption key spec for a ModelDeploymentMonitoringJob. If set, this ModelDeploymentMonitoringJob and all sub-resources of this ModelDeploymentMonitoringJob will be secured by this key.
endpoint	core	string	Required. Endpoint resource name. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
error	core	json	Output only. Only populated when the job's state is `JOB_STATE_FAILED` or `JOB_STATE_CANCELLED`.
gcp_display_name	core	string	Required. The user-defined name of the ModelDeploymentMonitoringJob. The name can be up to 128 characters long and can consist of any UTF-8 characters. Display name of a ModelDeploymentMonitoringJob.
labels	core	array<string>	The labels with user-defined metadata to organize your ModelDeploymentMonitoringJob. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
latest_monitoring_pipeline_metadata	core	json	Output only. Latest triggered monitoring pipeline metadata.
log_ttl	core	string	The TTL of BigQuery tables in user projects which stores logs. A day is the basic unit of the TTL and we take the ceil of TTL/86400(a day). e.g. { second: 3600} indicates ttl = 1 day.
logging_sampling_strategy	core	json	Required. Sample Strategy for logging.
model_deployment_monitoring_objective_configs	core	json	Required. The config for monitoring objectives. This is a per DeployedModel config. Each DeployedModel needs to be configured separately.
model_deployment_monitoring_schedule_config	core	json	Required. Schedule config for running the monitoring job.
model_monitoring_alert_config	core	json	Alert config for model monitoring.
name	core	string	Output only. Resource name of a ModelDeploymentMonitoringJob.
next_schedule_time	core	timestamp	Output only. Timestamp when this monitoring pipeline will be scheduled to run for the next round.
organization_id	core	string
parent	core	string
predict_instance_schema_uri	core	string	YAML schema file uri describing the format of a single instance, which are given to format this Endpoint's prediction (and explanation). If not set, we will generate predict schema from collected predict requests.
project_id	core	string
project_number	core	string
region_id	core	string
resource_name	core	string
satisfies_pzi	core	bool	Output only. Reserved for future use.
satisfies_pzs	core	bool	Output only. Reserved for future use.
schedule_state	core	string	Output only. Schedule state when the monitoring job is in Running state.
state	core	string	Output only. The detailed state of the monitoring job. When the job is still creating, the state will be 'PENDING'. Once the job is successfully created, the state will be 'RUNNING'. Pause the job, the state will be 'PAUSED'. Resume the job, the state will return to 'RUNNING'.
stats_anomalies_base_directory	core	json	Stats anomalies base folder path.
tags	core	hstore_csv
update_time	core	timestamp	Output only. Timestamp when this ModelDeploymentMonitoringJob was updated most recently.
zone_id	core	string