This article describes how to create and configure a Peak workflow that will automate the end-to-end process that is required to train and deploy an Amazon Personalize solution.


Contents


Before you start

  • Ensure your data is available in Redshift
    All interaction, item and user data must be imported into a Redshift table on the Peak platform.
    For details of how to access data from the Peak platform, see Data Sources.
  • Determine your recommendation use case
    This is so that you can identify the data that you’ll need to import and the recipe to use to train the model.|
    For a description of the datasets and recipes that Amazon Personalize uses, see: Amazon Personalize: Concepts and Terminology.


Process Overview

Peak users can manage the whole process using the Workflows functions.

For a guide to using Workflows, see What are Workflows? and Managing and Controlling Workflows.


To get to the Workflow screens:

  • Go to Factory > Workflows.


To configure a Workflow for Amazon Personalize, you will need to:

  1. Create a new workflow and set a trigger schedule.
  2. Map your data from your Redshift table to the Personalize datasets 
  3. Configure the model training parameters
  4. Deploy an API endpoint