Centralized repository and data sharing hub for establishing model sufficiency

1 . A system for centralized transfer of model input data, comprising:

a processor; and

a memory storing instructions that when executed by the processor, cause the processor to:

receive a dataset including data that is suitable to use as input to model behavior;

determine, based on a plurality of sufficiency parameters in a sufficiency database, an actual sufficiency of the dataset for feedback to train an artificial intelligence program, wherein the plurality of sufficiency parameters are associated with one or more of a plurality of datasets, the plurality of datasets including the dataset, each dataset associated with a respective version;

train the artificial intelligence program to generate a dataset sufficiency-indicator for the dataset based on training data comprising the plurality of sufficiency parameters in the sufficiency database;

generate, by the trained artificial intelligence program, the dataset sufficiency-indicator for the dataset;

generate a tag that encodes the dataset sufficiency-indicator;

store the tag in association with the version of the dataset in the sufficiency database;

determine that the dataset sufficiency-indicator for the dataset is below a purge value;

receive additional data comprising: (i) determined sufficiency parameters for previous versions of the sufficiency database, and (ii) external sufficiency parameters associated with an external dataset, the external sufficiency parameters comprising a real-time sufficiency adjustment;

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

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

determine that the another dataset sufficiency-indicator for the dataset is above the purge value;

based on the determination that the another dataset sufficiency-indicator for the dataset is above the purge value, communicate, via a network, a notification comprising an indication that the another dataset sufficiency-indicator for the dataset is above the purge value; and

retrain the artificial intelligence program based on the another dataset sufficiency-indicator.

2 . The system of claim 1 , wherein the actual sufficiency includes a value of the dataset.

3 . The system of claim 1 , wherein the data of the dataset comprises synthetic data.

4 . The system of claim 1 , wherein the instructions, when executed by the processor, cause the processor to:

generate, from the data of the dataset, a synthetic dataset including synthetic data suitable for a subsequent transfer.

5 . The system of claim 1 , wherein the plurality of sufficiency parameters include at least one of an actual sufficiency for the respective dataset, a size of the respective dataset, a time-period since a transfer of the respective dataset, a granularity of the data of the respective dataset, a system retention time between when the previously transferred dataset was received by the system and the transfer of the respective dataset, or a population associated with the respective dataset.

6 . The system of claim 5 , wherein the real-time sufficiency adjustment includes at least one 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 retention time before 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.

7 . The system of claim 1 , wherein the dataset sufficiency-indicator is an inference of the artificial intelligence program.

8 . The system of claim 1 , wherein the artificial intelligence program comprises a machine learning algorithm.

9 . The system of claim 1 , wherein the artificial intelligence program comprises a neural network.

10 . The system of claim 1 , wherein the instructions, when executed by the processor, cause the processor to:

generate another tag that encodes the another dataset sufficiency-indicator;

store the another tag in association with the version of the dataset in the sufficiency database.

11 . The system of claim 10 , wherein the additional data further comprises a synthetic dataset including synthetic data generated based on the dataset.

12 . A computer-implemented method, comprising:

accessing, by a processor, a dataset including data that is suitable to use as input to model behavior;

determining, by the processor based on a plurality of sufficiency parameters in a sufficiency database, an actual sufficiency of the dataset, wherein the plurality of sufficiency parameters are associated with one or more of a plurality of datasets, the plurality of datasets including the dataset, each dataset associated with a respective version;

training, by the processor, an artificial intelligence program to generate a dataset sufficiency-indicator for the dataset based on training data comprising the plurality of sufficiency parameters in the sufficiency database;

generating, by the trained artificial intelligence program, the dataset sufficiency-indicator for the dataset;

generating, by the processor, a tag that encodes the dataset sufficiency-indicator;

storing, by the processor, the tag in association with the version of the dataset in the sufficiency database;

determining, by the processor, that the dataset sufficiency-indicator for the dataset is below a purge value;

receiving, by the processor, additional data comprising: (i) determined sufficiency parameters for previous versions of the sufficiency database, and (ii) external sufficiency parameters associated with an external dataset, the external sufficiency parameters comprising a real-time sufficiency adjustment;

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

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

determining, by the processor, that the another dataset sufficiency-indicator for the dataset is above the purge value;

based on the determination that the another dataset sufficiency-indicator for the dataset is above the purge value, communicating, by the processor via a network, a notification comprising an indication that the another dataset sufficiency-indicator for the dataset is above the purge value; and

retraining, by the processor, the artificial intelligence program based on the another dataset sufficiency-indicator.

13 . The computer-implemented method of claim 12 , further comprising:

generating, by the processor, another tag that encodes the another dataset sufficiency-indicator;

storing, by the processor, the another tag in association with the version of the dataset in the sufficiency database.

14 . The computer-implemented method of claim 13 , wherein the additional data further comprises a synthetic dataset including synthetic data generated based on the dataset.

15 . A non-transitory computer-readable storage medium including instructions that when executed by a processor, cause the processor to:

receive a dataset including data that is suitable to use as input to model behavior;

determine, based on a plurality of sufficiency parameters in a sufficiency database, an actual sufficiency of the dataset for feedback to train an artificial intelligence program, wherein the plurality of sufficiency parameters are associated with one or more of a plurality of datasets, the plurality of datasets including the dataset, each dataset associated with a respective version;

train the artificial intelligence program to generate a dataset sufficiency-indicator for the dataset based on training data comprising the plurality of sufficiency parameters in the sufficiency database;

generate, by the trained artificial intelligence program, the dataset sufficiency-indicator for the dataset;

generate a tag that encodes the dataset sufficiency-indicator;

store the tag in association with the version of the dataset in the sufficiency database;

determine that the dataset sufficiency-indicator for the dataset is below a purge value;

receive additional data comprising: (i) determined sufficiency parameters for previous versions of the sufficiency database, and (ii) external sufficiency parameters associated with an external dataset, the external sufficiency parameters comprising a real-time sufficiency adjustment;

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

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

determine that the another dataset sufficiency-indicator for the dataset is above the purge value;

based on the determination that the another dataset sufficiency-indicator for the dataset is above the purge value, communicate, via a network, a notification comprising an indication that the another dataset sufficiency-indicator for the dataset is above the purge value; and

retrain the artificial intelligence program based on the another dataset sufficiency-indicator.

16 . The non-transitory computer-readable storage medium of claim 15 , including instructions, which when executed by the processor, cause the processor to:

generate another tag that encodes the another dataset sufficiency-indicator;

store the another tag in association with the version of the dataset in the sufficiency database.

17 . The non-transitory computer-readable storage medium of claim 16 ,

wherein the additional data further comprises a synthetic dataset including synthetic data generated based on the dataset.