A Flexible Framework for Anomaly Detection via Dimensionality Reduction
This provides a practical tool for anomaly detection in high-dimensional data, particularly useful for online detection, active learning, and unbalanced datasets.
The authors tackled the challenge of anomaly detection in high-dimensional datasets by developing DRAMA, a flexible framework combining dimensionality reduction and unsupervised clustering. They demonstrated that DRAMA performs robustly and competitively with existing methods across simulated and real datasets up to 3000 dimensions.
Anomaly detection is challenging, especially for large datasets in high dimensions. Here we explore a general anomaly detection framework based on dimensionality reduction and unsupervised clustering. We release DRAMA, a general python package that implements the general framework with a wide range of built-in options. We test DRAMA on a wide variety of simulated and real datasets, in up to 3000 dimensions, and find it robust and highly competitive with commonly-used anomaly detection algorithms, especially in high dimensions. The flexibility of the DRAMA framework allows for significant optimization once some examples of anomalies are available, making it ideal for online anomaly detection, active learning and highly unbalanced datasets.