Creating a solution and a solution version - Amazon Personalize
Services or capabilities described in Amazon Web Services documentation might vary by Region. To see the differences applicable to the China Regions, see Getting Started with Amazon Web Services in China (PDF).

Creating a solution and a solution version

After you finish importing data, you are ready to create a solution. A solution refers to the combination of an Amazon Personalize recipe, customized parameters, and one or more solution versions (trained models).

To create a solution in Amazon Personalize, you do the following:

  1. Create a solution – Customize solution parameters and recipe-specific hyperparameters so the model meets your specific business needs. See Creating and configuring a solution. For a list of available recipes, see Choosing a recipe.

    By default, new solution versions use automatic training to create solution versions every 7 days. You can configure the training frequency.

  2. Create a solution version (train a model): For solutions that use automatic training, solution version creation starts automatically after your solution is active. You can still create solution versions manually. For solutions with automatic training turned off, you manually create a solution version. See Creating a solution version.

  3. Evaluate the solution version – Use the metrics Amazon Personalize generates from the new solution version to evaluate the performance of the model. See Evaluating an Amazon Personalize solution version with metrics.

Topics