Amazon Personalize can now use 10X more item attributes to improve relevance of recommendations
Amazon Personalize is a machine learning service which enables you to personalize your website, app, ads, emails, and more, with custom machine learning models which can be created in Amazon Personalize, with no prior machine learning experience. AWS is pleased to announce that Amazon Personalize now supports ten times more item attributes. Previously, you could use up to five item attributes while building an ML model in Amazon Personalize. This limit is now 50 attributes. You can now use more information about your items, for example, category, brand, price, duration, size, author, year of release etc., to increase the relevance of recommendations.
Amazon Personalize is a machine learning service which enables you to personalize your website, app, ads, emails, and more, with custom machine learning models which can be created in Amazon Personalize, with no prior machine learning experience. AWS is pleased to announce that Amazon Personalize now supports ten times more item attributes. Previously, you could use up to five item attributes while building an ML model in Amazon Personalize. This limit is now 50 attributes. You can now use more information about your items, for example, category, brand, price, duration, size, author, year of release etc., to increase the relevance of recommendations.
To add item data to Personalize you first define a schema, telling Personalize the column names of the item dataset and whether you are sending categorical or numerical values. You can then create a dataset with this schema, following which you can import your items as a CSV file via S3. After following the same steps for importing ‘user’ and ‘interactions’ dataset you can train custom private personalization models with a few clicks.
Increased limit for item metadata is now available in US East (N. Virginia, Ohio), US West (Oregon), Canada (Central), Europe (Ireland),and Asia Pacific (Sydney, Tokyo, Mumbai, Singapore, Seoul). Please visit the Amazon Personalize getting started guide for more information.