Quotas in Amazon Personalize - Amazon Personalize

Quotas in Amazon Personalize

The following sections contain information about Amazon Personalize guidelines and quotas.

Supported AWS Regions

For a list of AWS Regions that support Amazon Personalize, see AWS Regions and Endpoints in the Amazon Web Services General Reference.

Compliance

For more information about Amazon Personalize compliance programs, see AWS Compliance, AWS Compliance Programs, and AWS Services in Scope by Compliance Program.

Service Quotas

Your AWS account has the following quotas for Amazon Personalize.

Resource Quota
Interactions
Minimum number of unique combined historical and event interactions (after filtering by eventType and eventValueThreshold, if provided) required to train a model (create a solution version). 1000
Maximum number of interactions that are considered by a model during training. 500 million
Maximum number of distinct event types combined with total number of metadata columns in Interactions datasets. 10
Users
Minimum number of unique users, with at least 2 interactions each, required to train a model (create a solution version). 25
Maximum number of users that are considered by a model during training. 50 million
Maximum number of metadata fields for a Users dataset. 5
Items
Maximum number of items that are considered by a model during training. 750 thousand
Maximum number of metadata fields for an Items dataset. 50
Data Import APIs
Maximum rate of PutItems requests. 10/second
Maximum rate of PutUsers requests. 10/second
Maximum rate of PutEvents requests. 1000/second
Maximum number of events in a PutEvents call. 10
Maximum size of an event. 10 KB
Recipes
Maximum amount of data for an individual dataset (Users, Items, or Interactions) for HRNN, SIMS, Popularity-Count, and Personalized-Ranking recipes. 100 GB
Maximum amount of data for Interactions dataset for HRNN-metadata and HRNN-coldstart recipes. 100 GB
Maximum amount of combined data for Users and Items datasets for HRNN-metadata and HRNN-coldstart recipes. 5 GB
Maximum number of cold start items the HRNN-Coldstart recipe supports to train a model (create a solution version). 80,000
Minimum number of cold start items the HRNN-Coldstart recipe requires to train a model (create a solution version). 100
Filters
Maximum number of filters per account 10 filters
Maximum number of parameters for a filter expression. 5 parameters
Maximum number of parameters across all filters in a dataset group. 10 parameters
GetRecommendations / GetPersonalizedRanking Requests
Maximum transaction rate (GetRecommendations and GetPersonalizedRanking requests). 2500/sec
Maximum number of GetRecommendations requests per second per campaign. 500/sec
Maximum number of GetPersonalizedRanking requests per second per campaign. 500/sec
Batch Inference Jobs
Maximum number of input files in a batch inference job. 1000
Maximum size of batch inference job input. 1 GB
Maximum number of records per input file in a batch inference job. 50 million

Your AWS account has the following quotas per region for Amazon Personalize.

Resource Quota
Total number of active schemas. 500
Total number of active datasets. 500
Total number of active dataset groups. 500
Total number of active event trackers. 500
Total number of active solutions. 500
Total number of active campaigns. 5
Total number of pending or in progress batch inference jobs 5
Total number of pending or in progress solution versions 20

Requesting a Quota Increase

For adjustable quotas, you can request a quota increase. The following Amazon Personalize quotas are adjustable:

  • Total number of active campaigns

  • Maximum number of filters per account

  • Total number of pending or in progress batch inference jobs

  • Total number of pending or in progress solution versions

  • Maximum rate of PutEvents requests

To request a quota increase, use the Service Quotas console and follow the steps in the Requesting a Quota Increase section of the Service Quotas User Guide.