Azure Personalizer is a cloud-based API service that allows you to choose the best experience to show to your users, learning from their real-time behavior.
- Provide information about your users and content and receive the top action to show your users.
- No need to clean and label data before using Personalizer.
- Provide feedback to Personalizer when it is convenient to you.
- View real-time analytics.
- Use Personalizer as part of a larger data science effort to validate existing experiments.
How does Personalizer work?
Personalizer uses machine learning models to discover what action to rank highest in a context. Your client application provides a list of possible actions, with information about them; and information about the context, which may include information about the user, device, etc. Personalizer determines the action to take. Once your client application uses the chosen action, it provides feedback to Personalizer in the form of a reward score. After the feedback is received, Personalizer automatically updates its own model used for future ranks. Over time, Personalizer will train one model that can suggest the best action to choose in each context based on their features.
Read more about Azure Personalizer here:
- PREVIEW: Azure Cognitive Services Personalizer
https://azure.microsoft.com/en-us/services/cognitive-services/personalizer/
kurtsh
Kurt Shintaku's Blog 