What is it about?

We present a novel algorithm to detect anomalies. It is fast and easy to use, also having the source codes available for download. No parameter-tuning is necessary. The input is a set of numerical values that can be either the original form of the dataset, or features extracted from more complex data, such as images, fingerprints or audio files. The output is a set of anomalous instances.

Featured Image

Why is it important?

Our algorithm allows spotting anomalies in large data collections in a fraction of the time required by previous methods. Also, it is fully automatic by not requiring any parameter-running.

Read the Original

This page is a summary of: Fast and Scalable Outlier Detection with Sorted Hypercubes, October 2020, ACM (Association for Computing Machinery),
DOI: 10.1145/3340531.3412033.
You can read the full text:

Read

Resources

Contributors

The following have contributed to this page