Isolating rare events in large-scale applications using a backward approach
Résumé
While significant work in data mining has been dedicated to the detection of single outliers in the data, less research has approached the problem of isolating a group of outliers, i.e. rare events representing micro-clusters of less - or significantly less - than 1% of the whole dataset. This research issue is critical for example in medical applications. The problem is difficult to handle as it lies at the frontier between outlier detection and clustering and distinguishes by a clear challenge to avoid missing true positives. We address this challenge and propose a novel two-stage framework, based on a backward approach, to isolate abnormal groups of events in large datasets. The key of our backward approach is to first detect the core of the dense regions and then gradually augment them based on a density-driven condition. The framework outputs a small subset of the dataset that contains both outliers and rare events. Experiments are performed on both synthetic data and a medical application and compared against state-of-the-art outlier detection algorithms. The results show a very good performance of our approach and confirm the fact that dedicated algorithms are needed for the detection of rare events in large-scale applications.