Automatic detection of anomalies in electronic communications

US10769658B2 · kind B2 · utility

Assignee

• International Business Machines Corporation · US

Inventors

• Michelle L. Carlough · West Caldwell, US
• Christopher M. Curtin · Acworth, US
• Robert K. Parkin · San Francisco, US
• Joshua P. Schiffman · New York, US
• Zuochun Tang · San Francisco, US
• Richard T. Winchell · New York, US

Key dates

• Filing date: Sep 30, 2016
• Grant date: Sep 8, 2020
• Expiry date: Oct 27, 2036

Classification

• Technology area (CPC H): Electricity
• CPC primary: H04L51/18
• WIPO field: IT methods for management
• WIPO sector: Electrical engineering

Abstract

Embodiments described herein provide approaches for detecting anomalies in electronic communications. Specifically, a set of response metrics is obtained from each of a plurality of communications. Each of the plurality of communications is part of a communications batch. Based on an aggregation of the response metric over the plurality of communications, a response metric value for one or more of the set of response metrics is computed. This response metric value is compared to a predicted metric value corresponding to the response metric. Based on this comparison, it is determined whether the response metric value is anomalous. If the response metric value is anomalous, a remediation activity is performed.