After the model is validated, and provided the performance metrics are met, the final step is to deploy the model in production for real predictions. Once the model is deployed, the new data can be run against the model for realtime predictions. Typically, if the model requires a large dataset for providing predictions, the model is likely to be executed in the offline mode.
Predictions using a model
Get Industrial Internet Application Development now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
