Skip to content

Anomaly Detection: How to Artificially Increase your F1-Score with a Biased Evaluation Protocol

Anomaly detection is a widely explored domain in machine learning. Many models are proposed in the literature, and compared through different metrics measured on various datasets.
The most popular metrics used to compare performances are F1-score, AUC and AVPR.
In this paper, we show that F1-score and AVPR are highly sensitive to the contamination rate.
One consequence is that it is possible to artificially increase their values by modifying the train-test split procedure.
This leads to misleading comparisons between algorithms in the literature, especially when the evaluation protocol is not well detailed.
Moreover, we show that the F1-score and the AVPR cannot be used to compare performances on different datasets as they do not reflect the intrinsic difficulty of modeling such data.
Based on these observations, we claim that F1-score and AVPR should not be used as metrics for anomaly detection. We recommend a generic evaluation procedure for unsupervised anomaly detection, including the use of other metrics such as the AUC, which are more robust to arbitrary choices in the evaluation protocol.

Damien Fourure*, Muhammad Usama Javaid*, Nicolas Posocco*, Simon Tihon*, Anomaly Detection: How to Artificially Increase your F1-Score with a Biased Evaluation Protocol, In Proc. of The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2021.

* equal contributions

Click here to access the paper.

Share on linkedin
Share on twitter
Share on email

Releated Posts

15 Papers in 2021: the outputs

The only way to master knowledge is to explore and enrich it. As we look back on the year 2021, we are proud to say that our R&D department has published 15 peer-reviewed scientific papers this year. Find out the impacts of the published papers in our new article.
Read More

2021 Wrap Up

We got a deep dive into some of the most memorable moments of 2021.
Read More