By using AWS re:Post, you agree to the AWS re:Post Terms of Use
AWS re:Postre:Post

Building an Time series forecasting model

0

Hello,

I've been trying for a quite a few times for now to build a time series forecasting model on top of my data set which in general represents product sales in one month. I would like to build a time series forecasting model that could predict future sale for a period of one week or two. The problem occurs whenever I hit the Standard Build button to build a model because of not being able to Preview Model for this selected model type. In a period of several seconds after hitting Standard Build button I get an following error:

> Request failed. Canvas can't process your request right now. Try again in a few minutes, or contact your administrator and share the details below to resolve the issue. If you're an administrator or an individual user, contact AWS support and provide the following code: {} to resolve the issue.

Can someone help me with that? Fun fact: I tried as well establishing machine learning model from the Amazon SageMaker Canvas Immersion Day example of forecasting store sales. The exact same problem occurs even here.

Thank you and best regards

Topics
Machine Learning & AI
Tags
Amazon SageMaker Canvas
Language
English
MK
asked 2 years ago792 views
2 Answers
0
Accepted Answer

To me, the error message is too generic to identify the root cause. If your account is not working with AWS examples, it may be the mis-config of account settings or canvas pre-requisites. Please follow the instruction below to eliminate the issues:

  1. Make sure your AWS account is setting up properly, e.g. try other services - launching EC2 instances
  2. Make sure you have enough permission to navigate on your account - permission error will pop up on the top of the console
  3. Set up amazon Sagemaker domain - https://docs.aws.amazon.com/sagemaker/latest/dg/canvas-getting-started.html
  4. Try on different region, e.g. us-west-2, us-east-2
AWS
Jady
answered 2 years ago
0

Hello there,

thank you for the provided instructions. I've been able to make a time forecast after giving my user permissions to perform time series forecasting.

Thanks for the help & best regards

MK
answered 2 years ago
  • yann_stoneman
    2 years ago

    For future visitors to this question: AmazonForecastFullAccess permissions can be added via these instructions https://docs.aws.amazon.com/sagemaker/latest/dg/canvas-set-up-forecast.html

  • AWS-User-0741373
    2 years ago

    Hi,

    In case any one getting "Request failed. Canvas can't process your request right now. Try again in a few minutes, or contact your administrator and share the details below to resolve the issue" message. You need to update sagemaker domain settings. It gives you an option to create/attach IAM policy for "Time series forecasting" to the domain. After that refresh your canvas session, error will disappear.

    Thanks

  • stratosb
    7 months ago

    Hello everyone, I am attepting to follow the excellent guide of Viktoria Semaan on how to build stock price predictions: https://community.aws/tutorials/no-code-ai-with-sagemaker-canvas.

    I have carried out all steps of part 1 successfully but every time I attempt to start the part 2 (https://community.aws/tutorials/no-code-ai-with-sagemaker-canvas#part-2-building-predictions-with-sagemaker-canvas) I get the error:

    "Canvas can't process your request right now. Try again in a few minutes, or contact your administrator and share the details below to resolve the issue. If you're an administrator or an individual user, contact AWS support and provide the following code: <c694997f-7fb0-4239-8ed9-8696312d0083> to resolve the issue."

    I have enabled the "Enable time series forecasting" permission in the domain as some of you have suggested in here but it didn't help.

    Could you please help me?

    Thank you

You are not logged in. Log in to post an answer.

A good answer clearly answers the question and provides constructive feedback and encourages professional growth in the question asker.

Guidelines for Answering Questions

Relevant content