Getting Started (Console) - Amazon Personalize

Getting Started (Console)

In this exercise, you use the Amazon Personalize console to create a campaign that returns movie recommendations for a given user.

Before you start this exercise, review the Getting Started Prerequisites.

After you finish this exercise, see Clean Up Resources.

In this procedure, you first create a dataset group. Next, you create an Amazon Personalize user-item interaction dataset in the dataset group and a schema to match your training data. Next, you import your training data into the dataset.

To import training data

  1. Open the Amazon Personalize console at https://console.aws.amazon.com/personalize/ and sign in to your account.

  2. Choose Create dataset group.

  3. If this is your first time using Amazon Personalize, on the Create dataset group page, in New dataset group, choose Get started.

  4. In Dataset group details, for Dataset group name, specify a name for your dataset group. Your screen should look similar to the following:

  5. Choose Next.

  6. On the Create user-item interaction data page, in Dataset details, for Dataset name, specify a name for your dataset.

  7. In Schema details, for Schema selection, choose Create new schema. A minimal Interactions schema is displayed in the Schema definition field. The schema matches the headers you previously added to the ratings.csv file.

  8. For New schema name, specify a name for the new schema.

    Your screen should look similar to the following:

  9. Choose Next.

  10. On the Import user-item interaction data page, in Dataset import job details, for Dataset import job name, specify a name for your import job.

  11. For IAM service role, keep the default selection of Enter a custom IAM role ARN.

  12. For Custom IAM role ARN, specify the role that you created in Creating an IAM Role.

  13. In the informational dialog box named Additional S3 bucket policy required, follow the instructions to add the required Amazon S3 bucket policy.

  14. For Data location, specify where your movie data file is stored in Amazon Simple Storage Service (S3). Use the following syntax:

    s3://<name of your S3 bucket>/<folder path>/<CSV filename>

    Your screen should look similar to the following:

  15. Choose Finish. The data import job starts and the Dashboard Overview page is displayed.

  16. Initially, in Upload datasets, the User-item interaction data status is Create pending (followed by Create in progress), and the Create solutions - Start button is disabled.

    Note

    The time it takes for the data to be imported depends on the size of the dataset.

    When the data import job has finished, the User-item interaction data status changes to Active and the Create solutions - Start button is enabled. Your screen should look similar to the following:

  17. After the import job has finished, choose the Create solutions - Start button. The Create solution page is displayed.

In this procedure, you use the dataset that you imported in the previous step to train a model. A trained model is referred to as a solution version.

To create a solution

  1. If the Create solution page is not already displayed, in the navigation pane, under the dataset group that you created, choose the Solution creation Start button.

  2. For Solution name, specify a name for your solution.

  3. For Recipe, choose aws-user-personalization. Leave the optional Solution configuration fields unchanged.

    Your screen should look similar to the following:

  4. Choose Next to display the Create solution version screen.

    Your screen should look similar to the following:

  5. There's no need to modify the Solution config, so choose Finish. Model training starts and the Dashboard Overview page is displayed.

  6. Initially, in Create solutions, the Solution creation status is Create pending (followed by Create in progress), the Launch campaigns - Start button is disabled, and a banner is displayed on the top of the console showing the progress.

    Note

    The time it takes to train a model depends on the size of the dataset and the chosen recipe.

  7. After training has finished, in the navigation pane choose Dashboard and choose Create new campaign.

In this procedure, you create a campaign by deploying the solution version you created in the previous step.

To create a campaign

  1. If the Create new campaign page is not already displayed, in the navigation pane, in the dataset group that you created, choose Dashboard, and then choose Create new campaign.

  2. In Campaign details, for Campaign name, specify a name for your campaign.

  3. For Solution, choose the solution you created in the previous step and for Solution version ID keep the default.

  4. For Minimum provisioned transactions per second, keep the default of 1.

    Your screen should look similar to the following:

  5. Choose Create campaign. Campaign creation starts and the Campaign page appears with the Campaign inference section displayed.

    Your screen should look similar to the following:

    Note

    Creating a campaign takes time.

    After the campaign is created, the page is updated to show the Test campaign results section. Your screen should look similar to the following:

In this procedure, use the campaign that you created in the previous step to get recommendations.

To get recommendations

  1. In Test campaign results, for User ID, specify a value from the ratings dataset, for example, 83. For Filter name keep the default selection of None.

  2. Choose Get recommendations. The Recommended item ID list displays the recommended item IDs.

    Your screen should look similar to the following: