Feedback loop

By providing feedback on alerts, you can improve the model accuracy.
The current qualifications are:

• False Negative: there is an anomaly that the model has not raised.
• False Positive: the alert raised is not correct

When qualifying a data point as false positive or negative, Sifflet extracts data around that point to build a subsample on which to train the model. Then, Sifflet combines the model trained locally with the model trained on the entire time series to build predictions that are more consistent with your data.

• Expected: the alert was expected. For instance, it can come for an extraordinary event such as a peak in sales on Black Friday sales. The model will become more lenient, leading to a widening of the confidence band.
• Fixed: the alert has been fixed
• Known Error: it is a known issue but won't be fixed as it might not be the priority. The model will ignore this data point.

How to qualify a data point

You can qualify a data point by simply clicking on it. It will pop a qualification screen:

Examples

Example 1:
In the case below, an alert has been identified on May 1st. After investigation, the root cause has been identified by your team but won't fix it for now.
Since it will not be fixed any time soon, and in order to avoid impacting future predictions, you can set the Qualification to "Known Error".

Example 2:
In the case below, an alert has been identified on March 3rd. After investigation, it appears that the alert was inaccurate and that the model underestimated the expected value.

In order to improve future predictions, you can set the Qualification to "False Positive".
You can already see the impact after the next run: the model will be less likely to raise an alert by underestimating the expected value.