Model Audit

Audit pre and post model predictions and performance metrics to support model observability, explainability and drift management

---

Overview

This optional configuration provide the ability to audit predications to enable model retraining, feature and prediction drift management, model observability, and any local business governance requirements.

The configuration will dynamically create an in-memory database table, using the process name as the target table, and rest endpoints to enable direct access and export functions.

Use this feature to support external drift monitoring and model retraining

Example

pmml predictor:
  name: irisScorer
  model: ./models/iris_rf.pmml
  response field: flowerPrediction
  
  audit configuration:
    target schema: ml_audit
    queue capacity: 5000
    flush frequency: 300

Attributes

Attribute	Description	Data Type	Required
target schema	name of the target schema where the table will be created	String
queue capacity	Number of prediction results to queue before flushing to target table	Integer Default: 1000
flush frequency	Frequency the queue will be flushed to table as seconds	Long Default: 60 Seconds

Support

Contact Fractalworks for details