Closed ghost closed 2 years ago
Hi,
The requirements for training a model is to have 1000 records of combined interaction data (after filtering by eventType and eventValueThreshold, if provided). This information can be found in the documentation here.
You can use an event tracker and a call to the PutEvents operation to record your interactions.
After you have collected 1000+ interactions, you can chose a recipe and train a model.
Thank you @annainspace,
I am wondering how can I know that I reach to 1000 records when I use event tracker only (that means no historical record in S3 before)
Hi,
You can use an AWS lambda, together with CloudWatch to track your ingestion.
Another option is to periodically export the interactions dataset and check how many events have been recorded.
Hello there, I am trying to use personalize with real time event. When I push a bank csv file (with no header) to S3 and tried to use amplify to connect with personalize. But I do not know when I can ready build a model because if I choose a recipe then I got an error that I need 10000 records to ready.
Could you suggest me some ways to do it?
Thanks in advance!