search

aws / random-cut-forest-by-aws

An implementation of the Random Cut Forest data structure for sketching streaming data, with support for anomaly detection, density estimation, imputation, and more.
https://github.com/aws/random-cut-forest-by-aws
Apache License 2.0
206 stars 33 forks source link

Reduce noise from streaming normalization #390

Closed sudiptoguha closed 11 months ago

sudiptoguha commented 1 year ago

For extremely smooth time series, the normalization introduces spurious anomalies -- often these are resolved with larger outputAfter, but it would be useful to lower that for smaller values of outputAfter. Some of these have been fixed in 3.6 -> 3.7, but several more remain. See https://github.com/opensearch-project/data-prepper/issues/2783

sudiptoguha commented 1 year ago

Basic issues resolved -- kept open for further evaluation.

sudiptoguha commented 11 months ago

closed based on #395