US 11,055,717 B2
Below-the-line thresholds tuning with machine learning
Jian Cai, Forest Hills, NY (US); and Sunil J. Mathew, Brooklyn, NY (US)
Assigned to Oracle Financial Services Software Limited, Maharashtra (IN)
Filed by ORACLE FINANCIAL SERVICES SOFTWARE LIMITED, Mumbai (IN)
Filed on Sep. 28, 2018, as Appl. No. 16/145,952.
Prior Publication US 2020/0104849 A1, Apr. 2, 2020
Int. Cl. G06Q 20/40 (2012.01); G06N 20/00 (2019.01); G06K 9/62 (2006.01); G06Q 40/02 (2012.01)
CPC G06Q 20/4016 (2013.01) [G06K 9/6262 (2013.01); G06N 20/00 (2019.01); G06Q 40/02 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A non-transitory computer-readable medium storing computer-executable instructions that when executed by at least a processor of a computer cause the computer to:
select, by at least the processor, a set of sampled events from a set of historic events previously divided by an alerting engine into a set of below-the-line events and a set of above-the-line events separated by a threshold line indicating that an event is suspicious, wherein the threshold line is defined at least in part by one or more threshold values;
label, by at least the processor, each event in the set of sampled events as either suspicious or not suspicious;
build, by at least the processor, based at least in part on the set of sampled events, a machine learning model to calculate for a given event a probability that the given event is suspicious;
train, by at least the processor, the machine learning model;
validate, by at least the processor, that the machine learning model is calibrated;
determine, by at least the processor, based at least in part on one or more probabilities calculated by the machine learning model, a scenario and segment combination to be tuned;
generate, by at least the processor, a tuned threshold value in real-time based at least in part on the one or more probabilities calculated by the machine learning model; and
tune, by at least the processor, the alerting engine by replacing at least one of the one or more threshold values with the tuned threshold value in real-time to cause the threshold line to be adjusted to reduce errors by the alerting engine in classifying events as not suspicious.