Evaluating the performance of the real-time anomaly detection included in the Elastic Stack

I was quite new to the Elastic Stack and I managed to play a bit with it in the past month.
I am doing a Master Thesis on Anomaly Detection and I am using the Elastic Stack as part of it.

I have tried to look at the repository of the machine learning module of the Elastic stack, but It is pretty broad and I do not know where to find the Anomaly Detection part. Maybe you can point me in the right direction since it would be good to look at the exact code that makes things work.

Moreover, I would like to benchmark the Elasticsearch Anomaly Detection tool using the Numenta Anomaly Benchmark. These are the guidelines and entry points to run the benchmark on a custom Anomaly Detection algorithm. I was wondering, whether someone can give me some suggestions/wants to work on this with me.
Maybe someone tried to do this before and I would really love to have such precious feedback.

Do you think this will be too much for a master thesis scope? Considering it will not be my one and only focus.

Thank you in advance, any help would be really appreciated. :slight_smile:

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.