Reduce Amazon Personalize costs with these tips
Build real-time recommendations into your applications
Amazon Personalize cost saving tips
Optimize your Amazon Personalize costs with these tips
Delete Unused Models
Regularly review and delete your models and campaigns that are no longer needed. You are charged per model so this can lower costs.
Optimize Dataset Size
Use smaller dataset sizes and model types where possible to optimize costs. The guidance to do this is found in the AWS documentation
Auto-scaling
Use automatic scaling features to optimize resource provisioning for your workload, scaling up during peak usage and down when not needed.
Service information & pricing
About Amazon Personalize
- About Amazon Personalize
-
Amazon Personalize is a machine learning system that improves customer experiences and boosts revenue through data unification, loyalty promotion, and optimization of personalization engines. It provides real-time suggestions, aids digital transformation, and works well with existing platforms. Further, it enhances customer targeting, manages rule-based promotions, and uses data efficiently. It consequently leads to increased customer purchases and long-term engagement.
- Amazon Personalize pricing
-
Amazon Personalize operates on a pay-as-you-go scheme. Charging $0.05/GB for data storage and processing and $0.24 per training hour. Real-time recommendations cost $0.0556/1,000 for the initial 72 million requests, decreasing with increased usage. Batch recommendations cost $0.067/1,000 for the first 20 million and similarly decrease. Additional costs for specific features like including Item metadata in requests apply.