dotnet / dotnet/machinelearning

[AnomalyDetection] Some points marked as anomaly with little deviation

Open
#5,640 2 comments 0 reactions 0 assignees View on GitHub
area-TimeSeries Priority:2
Dominant language
C#
Stars
9.4k
Forks
2k
Avg merge
2d 20h
Merged PRs (30d)
11

Description

### System information

- **OS version/distro**:
- **.NET Version (eg., dotnet --info)**: master

### Issue

- **What did you do?** Apply AnomalyDetection API
- **What happened?** Some points are marked as anomaly while some others that look more like anomaly are not marked as anomaly.
- **What did you expect?** I expect the points that look has more deviations mark as anomaly, rather than the ones with small deviation.
![image](https://user-images.githubusercontent.com/3010893/109843877-6d44c600-7c00-11eb-8049-69d579ee8bdb.png)

Expecting the highlighted points with higher deviation to be anomalies.

**Please assign the issue** to: https://github.com/guinao and https://github.com/mengaims

### Source code / logs

var anomalyDetectorOptions = new SrCnnEntireAnomalyDetectorOptions()
{
DetectMode = //WithMargin,
Sensitivity = 20,
DeseasonalityMode = SrCnnDeseasonalityMode.Median,
Period = -1,
Threshold =0.18,
};

anomalyResult = this.mlContext.AnomalyDetection.DetectEntireAnomalyBySrCnn(
...
anomalyDetectorOptions);

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.