Granted Patent B2

US 12,724,847 · App. 17/661,800 · Granted Sep 1, 2026

Inventor: Daniel Caricato (Fort Mill, SC)

Assignee: TRUIST BANK

G06F18/214G06F16/2358

Abstract

Claims (58)

1 . A system for training a centralized transfer module to estimate the sufficiency of sets of data for modeling, the system comprising a computer including one or more processors and at least one of a memory device and a non-transitory storage device, wherein the one or more processors are configured to execute instructions to:

identify sufficiency parameters of a transferred dataset including data that is suitable to use as input to model behavior;

receive a communication indicating an actual sufficiency of the transferred dataset;

generate the sufficiency parameters of the transferred dataset in a sufficiency database utilizing a previous transfer module, the previous transfer module configured for interfacing with at least one previous version of a sufficiency listing, wherein the sufficiency parameters comprise: a size of the transferred dataset, a time-period since the transfer of the transferred dataset, a granularity of the data of the transferred dataset, a system retention time between when the transferred dataset was received by the system and the transfer of the transferred dataset, and a population associated with the transferred dataset;

train an artificial intelligence program of the centralized transfer module to generate a dataset sufficiency-indicator, the dataset sufficiency-indicator comprising an estimate of an actual sufficiency of an associated dataset for modeling, the dataset sufficiency-indicator generated by the artificial intelligence program based on the sufficiency parameters of the transferred dataset as input data and the actual sufficiency of the transferred dataset as a known output;

generate, by the artificial intelligence program, the dataset sufficiency-indicator for transferred dataset based on the sufficiency parameters for the transferred dataset in the sufficiency database and the actual sufficiency of the transferred dataset;

determine, based on a comparison, that the dataset sufficiency-indicator for the transferred dataset is less than a purge value;

receive additional data comprising: (i) previous sufficiency parameters generated from a previous version of the sufficiency listing with corresponding actual sufficiency values, and (ii) external sufficiency parameters associated with an external dataset, the external sufficiency parameters comprising a real-time sufficiency adjustment, the real-time sufficiency adjustment comprising: an inflation indicator, a consumer confidence indicator, a consumer sentiment indicator, a size of the external dataset, a time-period since a transfer of the external dataset, a granularity of the data of the external dataset, a system retention time between when the external dataset was received by the system and the transfer of the external dataset, a population associated with the external dataset, a sufficiency indicator for the external dataset, and an actual sufficiency for the transfer of the external dataset;

update the artificial intelligence program based on the additional data;

generate, by the updated artificial intelligence program, another dataset sufficiency-indicator for the transferred dataset;

determine that the another dataset sufficiency-indicator for the transferred dataset is greater than the purge value; and

based on the determination that the another dataset sufficiency-indicator for the transferred dataset is greater than the purge value, update a tag associated with the transferred dataset.

2 . The system of claim 1 , wherein the one or more processors are further configured to execute instructions to:

modify the sufficiency listing to eliminate a representation of the transferred dataset from the sufficiency listing.

3 . The system of claim 1 , wherein the one or more processors are further configured to execute instructions to:

modify the sufficiency listing to eliminate the dataset sufficiency-indicator for the transferred dataset from the sufficiency listing.

4 . The system of claim 1 , wherein the one or more processors are further configured to execute instructions to:

modify at least one of the transferred dataset or a representation of the transferred dataset within the sufficiency listing to remove a tag representative of the dataset sufficiency-indicator for the transferred dataset.

5 . The system of claim 1 , wherein the instruction to train the artificial intelligence program of the centralized transfer module includes utilizing a previously generated dataset sufficiency-indicator for the transferred dataset.

6 . The system of claim 5 , wherein the previously generated dataset sufficiency-indicator for the transferred dataset is indicated as at least one of a satisfactory inference or an unsatisfactory inference.

7 . The system of claim 1 , wherein the actual sufficiency includes a value of the dataset, wherein updating the artificial intelligence program comprises modifying one or more weights of the artificial intelligence program.

8 . The system of claim 1 , wherein the one or more processors are further configured to execute instructions to:

communicate, to another device based on the determination that the another dataset sufficiency-indicator for the transferred dataset is greater than the purge value, a notification comprising an indication that the another dataset sufficiency-indicator for the transferred dataset is greater than the purge value and a recommendation to initiate transfer of the transferred dataset.

9 . The system of claim 1 , wherein the additional data comprises user feedback, wherein the artificial intelligence program is updated based on the user feedback.

10 . The system of claim 9 , wherein the user feedback comprises positive feedback for the previous version of the sufficiency listing and negative feedback for another previous version of the sufficiency listing.

11 . The system of claim 10 , wherein the real-time sufficiency adjustment is injected into the artificial intelligence program as additional features for updating such that weights of the artificial intelligence program are updated.

12 . The system of claim 11 , wherein the artificial intelligence program weights the system retention time as a feature during training and updating, thereby configuring the dataset sufficiency-indicator to reflect the system retention time.

13 . A system for training a centralized transfer module to estimate the sufficiency of datasets for modeling, the system comprising a computer including one or more processors and at least one of a memory device and a non-transitory storage device, wherein the one or more processors are configured to execute instructions to:

receive a communication indicating an actual sufficiency of a transferred dataset;

communicate with a sufficiency database to receive sufficiency parameters of the transferred dataset, wherein the sufficiency parameters of the transferred dataset are generated in the sufficiency database utilizing a previous transfer module configured for interfacing with at least one previous version of a sufficiency listing, wherein the sufficiency parameters comprise: a size of the transferred dataset, a time-period since the transfer of the transferred dataset, a granularity of the data of the transferred dataset, a system retention time between when the transferred dataset was received by the system and the transfer of the transferred dataset, and a population associated with the transferred dataset;

train an artificial intelligence program of the centralized transfer module to generate a dataset sufficiency-indicator, the dataset sufficiency-indicator comprising an estimate of an actual sufficiency of an associated dataset for modeling, the dataset sufficiency-indicator generated by the artificial intelligence program based on the sufficiency parameters of the transferred dataset as input data and the actual sufficiency of the transferred dataset as a known output;

generate, by the artificial intelligence program, the dataset sufficiency-indicator for transferred dataset based on the sufficiency parameters for the transferred dataset in the sufficiency database and the actual sufficiency of the transferred dataset;

determine, based on a comparison, that the dataset sufficiency-indicator for the transferred dataset is less than a purge value;

receive additional data comprising: (i) previous sufficiency parameters generated from a previous version of the sufficiency listing with corresponding actual sufficiency values, and (ii) external sufficiency parameters associated with an external dataset, the external sufficiency parameters comprising a real-time sufficiency adjustment, the real-time sufficiency adjustment comprising: an inflation indicator, a consumer confidence indicator, a consumer sentiment indicator, a size of the external dataset, a time-period since a transfer of the external dataset, a granularity of the data of the external dataset, a system retention time between when the external dataset was received by the system and the transfer of the external dataset, a population associated with the external dataset, a sufficiency indicator for the external dataset, and an actual sufficiency for the transfer of the external dataset;

update, based on the additional data, the artificial intelligence program;

generate, by the updated artificial intelligence program, another dataset sufficiency-indicator for the transferred dataset;

determine that the another dataset sufficiency-indicator for the transferred dataset is greater than the purge value; and

based on the determination that the another dataset sufficiency-indicator for the transferred dataset is greater than the purge value, update a tag associated with the transferred dataset.

14 . The system of claim 13 , wherein the one or more processors are further configured to execute instructions to:

modify the sufficiency listing to eliminate a representation of the transferred dataset from the sufficiency listing.

15 . The system of claim 13 , wherein the one or more processors are further configured to execute instructions to:

modify the sufficiency listing to eliminate a dataset sufficiency-indicator for the transferred dataset from the sufficiency listing.

16 . The system of claim 13 , wherein the instruction to train the artificial intelligence program of the centralized transfer module includes utilizing a previously generated dataset sufficiency-indicator for the transferred dataset.

17 . The system of claim 13 , wherein the actual sufficiency includes a value of the dataset.

18 . A method for training a centralized transfer module to estimate the sufficiency of sets of data for modeling, the method comprising:

identifying, by a processor, sufficiency parameters of a transferred dataset including data that is suitable to use as input to model behavior;

receiving, by the processor, a communication indicating an actual sufficiency of the transferred dataset;

generating, by the processor, the sufficiency parameters of the transferred dataset in a sufficiency database utilizing a previous transfer module, the previous transfer module configured for interfacing with at least one previous version of a sufficiency listing, wherein the sufficiency parameters comprise: a size of the transferred dataset, a time-period since the transfer of the transferred dataset, a granularity of the data of the transferred dataset, a system retention time between when the transferred dataset was received by the processor and the transfer of the transferred dataset, and a population associated with the transferred dataset;

training, by the processor, an artificial intelligence program of the centralized transfer module to generate a dataset sufficiency-indicator, the dataset sufficiency-indicator comprising an estimate of an actual sufficiency of an associated dataset, the dataset sufficiency-indicator generated by the artificial intelligence program based on the sufficiency parameters of the transferred dataset as input data and the actual sufficiency of the transferred dataset as a known output;

generating, by the artificial intelligence program, the dataset sufficiency-indicator for transferred dataset based on the sufficiency parameters for the transferred dataset in the sufficiency database and the actual sufficiency of the transferred dataset;

determining, by the processor based on a comparison, that the dataset sufficiency-indicator for the transferred dataset is less than a purge value;

receiving, by the processor, additional data comprising: (i) previous sufficiency parameters generated from a previous version of the sufficiency listing with corresponding actual sufficiency values, and (ii) external sufficiency parameters associated with an external dataset, the external sufficiency parameters comprising a real-time sufficiency adjustment, the real-time sufficiency adjustment comprising: an inflation indicator, a consumer confidence indicator, a consumer sentiment indicator, a size of the external dataset, a time-period since a transfer of the external dataset, a granularity of the data of the external dataset, a system retention time between when the external dataset was received by the processor and the transfer of the external dataset, a population associated with the external dataset, a sufficiency indicator for the external dataset, and an actual sufficiency for the transfer of the external dataset;

updating, by the processor based on the additional data, the artificial intelligence program;

generating, by the updated artificial intelligence program, another dataset sufficiency-indicator for the transferred dataset;

determining, by the processor, that the another dataset sufficiency-indicator for the transferred dataset is greater than the purge value; and

based on the determination that the another dataset sufficiency-indicator for the transferred dataset is greater than the purge value, updating a tag associated with the transferred dataset.

19 . The method of claim 18 , wherein training the artificial intelligence program of the centralized transfer module includes utilizing a previously generated dataset sufficiency-indicator for the transferred dataset.

20 . The method of claim 18 , wherein the actual sufficiency includes a value of the dataset.

Assignments (1)

Continuity (1)

References Cited (27)