We consider the problem of anomaly detection in finance. An application of interest is the detection of first-time fraud where new classes of fraud need to be detected using unsupervised learning to augment the existing supervised learning techniques that capture known classes of frauds. This domain usually has the following requirements - (i) the ability to handle data containing both numerical and categorical features, (ii) very low latency real-time detection, and (iii) interpretability. We propose the use of a variant of density estimation trees (DETs) (Ram and Gray, 2011) for anomaly detection using distributional properties of the data. We formally present a procedure for handling data sets with both categorical and numerical features while Ram and Gray (2011) focused mainly on data sets with all numerical features. DETs have demonstrably fast prediction times, orders of magnitude faster than other density estimators like kernel density estimators. The estimation of the density and the anomalousness score for any new item can be done very eciently. Beyond the flexibility and effciency, DETs are also quite interpretable. For the task of anomaly detection, DETs can generate a set of decision rules that lead to high anomalous-ness scores. We empirically demonstrate these capabilities on a publicly available fraud data set.
展开▼
