Note on the curse of dimensionality regarding financial anomaly detection

The so-called curse of dimensionality represents limitations to the processes of manipulation, interpretation and analysis of high dimensional data, which makes identifying behaviour patterns in cursed dimensional feature spaces complex. Several recently published articles discussed the need to use dimensionality reduction methods when considering the issue of detecting anomalies in financial systems. However, most articles developed models that did not consider real-time data or the continuous generation of information. They also did not directly address how to overcome situations arising from a great volume of data. This short communication reports on articles that used voluminous but static data, and articles that used real-time data to identify anomalies in financial systems but did not significantly address the issues related to dimensionality. Furthermore, this note signals the need for further investigation of how to break the curse of dimensionality through developing financial anomaly detection models to promote better decision support systems.