US 11,748,463 B2
Fraud detection in interactive voice response systems
Scott Strong, Atlanta, GA (US); Kailash Patil, Atlanta, GA (US); David Dewey, Atlanta, GA (US); Raj Bandyopadhyay, Atlanta, GA (US); Telvis Calhoun, Atlanta, GA (US); and Vijay Balasubramaniyan, Atlanta, GA (US)
Assigned to PINDROP SECURITY, INC., Atlanta, GA (US)
Filed by PINDROP SECURITY, INC., Atlanta, GA (US)
Filed on Jan. 25, 2021, as Appl. No. 17/157,837.
Application 17/157,837 is a continuation of application No. 16/515,823, filed on Jul. 18, 2019, granted, now 10,902,105.
Application 16/515,823 is a continuation of application No. 15/880,287, filed on Jan. 25, 2018, granted, now 10,362,172, issued on Jul. 23, 2019.
Application 15/880,287 is a continuation of application No. 15/294,538, filed on Oct. 14, 2016, granted, now 9,883,040, issued on Jan. 30, 2018.
Claims priority of provisional application 62/371,103, filed on Aug. 4, 2016.
Claims priority of provisional application 62/241,478, filed on Oct. 14, 2015.
Prior Publication US 2021/0150010 A1, May 20, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 21/32 (2013.01); G06N 20/00 (2019.01); G06F 21/55 (2013.01); H04M 3/493 (2006.01); H04W 12/128 (2021.01); H04M 3/527 (2006.01); H04M 15/00 (2006.01); H04W 12/12 (2021.01); H04M 7/00 (2006.01)
CPC G06F 21/32 (2013.01) [G06F 21/552 (2013.01); G06N 20/00 (2019.01); H04M 3/493 (2013.01); H04M 3/527 (2013.01); H04M 15/41 (2013.01); H04W 12/12 (2013.01); H04W 12/128 (2021.01); H04M 7/0078 (2013.01); H04M 2203/551 (2013.01); H04M 2203/6027 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
obtaining, by a computer, call data for an incoming call indicating a source automatic number identification (ANI) and one or more user accounts corresponding to the source ANI in the call data for the incoming call;
extracting during the incoming call, by the computer, one or more features for the incoming call using the call data for the incoming call;
extracting during the incoming call, by the computer, a feature vector for the incoming call based upon the one or more features extracted using the call data for the incoming call; and
generating, by the computer, a risk score for the incoming call by executing a machine learning model on the feature vector generated for the incoming call, the machine learning model trained on the call data of a plurality of past calls, a plurality of source ANIs, and a plurality of user accounts corresponding to the plurality of source ANIs.