0

I have started studying anomaly detector. According to my use case multivariate anomaly detector is good.

I have created a model with my base data with HTTP post API (https://{endpoint}/anomalydetector/v1.1/multivariate/models)

and tested anomaly in the new data with another HTTP post API (https://{endpoint}/anomalydetector/v1.1/multivariate/models/{modelId}:detect-last)

It is working fine. Now I want to add more data to my existing model and train it better.

For Example:

I have generated a multivariate anomaly model with data from 1st January 2023 to 31st January 2023. Used that model to find the anomaly in the data of February 2023.

On the 1st March 2023 I want to add data from 1st February 2023 to 28th February 2023 to that existing model. So that the model becomes more mature with new data and give me better result in March 2023.

I am not able to find any way to do that. Whenever I try to post created model request (https://{endpoint}/anomalydetector/v1.1/multivariate/models) with the same model name and csv file name, it created new model. So my questions are,

Is it possible to add more data points to existing model?

If yes, How?

If no, Is there any other option or service that I can use?

Improve this question

1 Answer 1

Reset to default
0

Use Train Model API to create and train a model, then use Get Model Status API to get the status and model metadata.

https://learn.microsoft.com/en-us/azure/cognitive-services/anomaly-detector/how-to/train-model

Improve this answer
1
  • Thanks, Ramprasad for the response. I have already created a model. I want to add more data points to the existing model and train it. You can considering it like editing model.
    – Yash
    Commented Apr 25, 2023 at 13:28

Not the answer you're looking for? Browse other questions tagged or ask your own question.