Model maintenance
Periodically a model rerun is necessary to prevent model staleness due to changes in the
input datasets in Data Lake over a period of time.
As the input data distribution changes, the performance of the model weakens over time. Depending on the frequency of the data variations, you can update the model manually or schedule an automatic model update.
While the existing endpoint is being redeployed, the endpoint does not have a downtime if it is still active. After the updated endpoint is created, it replaces the existing endpoint.