Overview of Amazon Personalize and pricing
Amazon Personalize is a fully managed machine learning service that goes beyond rigid static rule based recommendation systems and trains, tunes, and deploys custom ML models to deliver highly customized recommendations to customers across industries such as retail and media and entertainment.
It has the following features
- Automated machine learning
- Real-time recommendations
- Batch recommendations
- New user and new item recommendations
- Contextual recommendations
- Similar item recommendations
- Unlock Information in Unstructured Text
How it works
Use Cases
Amazon Personalize is predominantly utilized for Personalized Recommendations applications and has the following use cases
- Deliver high quality recommendations, in real-time
- Easily implement personalized recommendations in days, not months
- Personalize every touchpoint along the customer journey
- Data privacy and security
Amazon Personalize Pricing
With Amazon Personalize, you pay only for what you use, and there are no minimum fees and no upfront commitments. You are charged based on the amount of data processed and stored, the compute hours used to train your models, and for the throughput of recommendations.
For example, if a media company would like to utilize Amazon Personalize for their movie title recommendations, following is the sample calculator
| Type of Charge | Assumptions | Price | Cost |
| Data processing and storage charge | 200 GB of Item, users and Interactions Data | 200 GB * $0.05 per GB | $10 |
| User Charges | 100,000 users for 2 recommeders | $0.375 per hour * 732 hours per month * 2 recommenders | $549 |
| Total Cost | $559 |
Following will provide additional details for Amazon Personalize Pricing – https://aws.amazon.com/personalize/pricing/