Methods and systems for anomaly detection in small datasets
US7729964B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 27, 2004 |
| Grant date | Jun 1, 2010 |
| Priority date | — |
| Expiry date | Apr 29, 2027 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06Q40/04
- WIPO fieldIT methods for management
- WIPO sectorElectrical engineering
Abstract
A technique for detecting anomalous values in a small set of financial metrics makes use of context data that is determined based upon the characteristics of the target company being evaluated. Context data is selected to represent the historical values of the financial metric for the target company or the simultaneous performance of peer companies. Using the context data, an anomaly score for the financial metric is calculated representing the degree to which the value of the financial metric is an outlier among the context data. This can be done using an exceptional statistical technique. The anomaly score can be used to evaluate the risks associated with business transactions related to the target company.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.