US 12,327,223 B2
Systems and methods for retraining an artificial intelligence engine
Sriram Raghavan, Orlando, FL (US)
Assigned to Truist Bank, Charlotte, NC (US)
Filed by Truist Bank, Charlotte, NC (US)
Filed on May 3, 2024, as Appl. No. 18/654,420.
Application 18/654,420 is a continuation of application No. 17/744,105, filed on May 13, 2022, granted, now 12,020,215.
Application 17/744,105 is a continuation of application No. 17/717,312, filed on Apr. 11, 2022, granted, now 11,941,586, issued on Mar. 26, 2024.
Prior Publication US 2024/0289751 A1, Aug. 29, 2024
Int. Cl. G06Q 10/1093 (2023.01); G06N 3/044 (2023.01)
CPC G06Q 10/1095 (2013.01) [G06N 3/044 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A computing system, comprising:
at least one processor;
a communication interface communicatively coupled to the at least one processor; and
one or more memory devices storing executable code, wherein execution of the executable code causes the at least one processor to:
train, using a first set of training test data, an artificial intelligence engine to correlate event parameters with binary event scores to predict optimal parameters, the training using an iterative training and testing loop that iteratively tests the first set of training test data compared to a target variable and makes adjustments in subsequent iterations to improve predictability of the target variable thereby improving accuracy of the artificial intelligence engine;
deploy the trained artificial intelligence engine;
receive, via a network and from a facilitator device, a plurality of event parameters as part of a feedback loop to improve predictability of the trained artificial intelligence engine;
receive, from one or more user devices, one or more binary event scores as part of the feedback loop to be used as a second set of training test data to retrain the artificial intelligence engine;
retrain the trained artificial intelligence engine using the second set of training test data; and
deploy the retrained artificial intelligence engine to predict the optimal parameters for one or more new events; and
transmit the predicted optimal parameters for the one or more new events to the facilitator device.