US 11,385,943 B2Granted

System, method, and computer-accessible medium for evaluating multi-dimensional synthetic data using integrated variants analysis

AssigneeCapital One Services, LLC

InventorsMark Watson, Fardin Abdi Taghi Abad, Anh Truong, Kenneth Taylor, Reza Farivar, Jeremy Goodsitt, Austin Walters, Vincent Pham

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

An exemplary system, method, and computer-accessible medium can include, for example, receiving an original dataset(s), receiving a synthetic dataset(s), training a model(s) using the original dataset(s) and the synthetic dataset(s), and evaluating the synthetic dataset(s) based on the training of the model(s). The model(s) can include a first model and a second model, and the first model can be trained using the original dataset(s) and the second model can be trained using the synthetic dataset(s). The synthetic dataset(s) can be evaluated by comparing first results from the training of the first model to second results from the training of the second model.

Claims20

Dependent claims

A non-transitory computer-accessible medium having stored thereon computer-executable instructions for evaluating at least one synthetic dataset, wherein, when a computer arrangement executes the instructions, the computer arrangement is configured to perform procedures comprising:

receiving at least one original dataset;
receiving the at least one synthetic dataset;
training at least one model using the at least one original dataset and the at least one synthetic dataset;
generating a statistical correlation score based on the at least one synthetic dataset and the at least one original dataset;
generating a univariate distribution score based on the at least one synthetic dataset and the at least one original dataset;
generating an evaluation score by evaluating the at least one synthetic dataset based on the training of the least one model, wherein the evaluation score includes the statistical correlation score and the univariate distribution score;
determining a region for the at least one synthetic dataset based on the evaluation score, wherein the region includes one of
(i) a normal region where the at least one synthetic dataset is unlikely to contain synthetic data that is similar to original data within the at least one original dataset,
(ii) a warning region where the at least one synthetic dataset at least one of (a) potentially contains the synthetic data that is similar to the original data or (b) the synthetic data does not substantially match a schema of the at least one original dataset, or
(iii) a red flag region where the at least one synthetic dataset is likely to contain the synthetic data that is similar to the original data;
and
generating a suggestion based on the evaluation score and the determined region, wherein the suggestion includes one of (i) indicating that the at least one synthetic dataset is adequate or (ii) warning that the at least one synthetic dataset potentially contains information similar to the at least one original dataset.

9 more elements

A method for evaluating at least one synthetic dataset, comprising:

receiving at least one original dataset;
generating the at least one synthetic dataset based on the at least one original dataset;
training at least one first model using the at least one original dataset;
training at least one second model using the at least one synthetic dataset;
generating a statistical correlation score based on the at least one synthetic dataset and the at least one original dataset;
generating a univariate distribution score based on the at least one synthetic dataset and the at least one original dataset;
using a computer arrangement, generating an evaluation score by evaluating the at least one synthetic dataset based on the training of the least one first model and the training of the at least one second model, wherein the evaluation score includes the statistical correlation score and the univariate distribution score;
determining a region for the at least one synthetic dataset based on the evaluation score, wherein the region includes one of
(i) a normal region where the at least one synthetic dataset is unlikely to contain synthetic data that is similar to original data within the at least one original dataset,
(ii) a warning region where the at least one synthetic dataset at least one of (a) potentially contains the synthetic data that is similar to the original data or (b) the synthetic data does not substantially match a schema of the at least one original dataset, or
(iii) a red flag region where the at least one synthetic dataset is likely to contain the synthetic data that is similar to the original data;
and
generating a suggestion based on the evaluation score and the determined region, wherein the suggestion includes one of (i) indicating that the at least one synthetic dataset is adequate or (ii) warning that the at least one synthetic dataset potentially contains information similar to the at least one original dataset.

10 more elements

A system, comprising:

a computer hardware arrangement configured to:
(a) receive at least one original dataset;
(b) receive at least one synthetic dataset related to the at least one original dataset;
(c) train at least one first model using the at least one original dataset;
(d) train at least one second model using the at least one synthetic dataset;
(e) generate a statistical correlation score based on the at least one synthetic dataset and the at least one original dataset;
(f) generate a univariate distribution score based on the at least one synthetic dataset and the at least one original dataset;
(g) generate an evaluation score by comparing first results from the training of the first model to second results from the training of the second model, wherein the evaluation score includes the statistical correlation score and the univariate distribution score;
(h) determine a region for the at least one synthetic dataset based on the evaluation score, wherein the region includes one of
(i) a normal region where the at least one synthetic dataset is unlikely to contain synthetic data that is similar to original data within the at least one original dataset,
(ii) a warning region where the at least one synthetic dataset at least one of (a) potentially contains the synthetic data that is similar to the original data or (b) the synthetic data does not substantially match a schema of the at least one original dataset, or
(iii) a red flag region where the at least one synthetic dataset is likely to contain the synthetic data that is similar to the original data;
and
(i) generate a suggestion based on the evaluation score and the determined region, wherein the suggestion includes one of (i) indicating that the at least one synthetic dataset is adequate or (ii) warning that the at least one synthetic dataset potentially contains information similar to the at least one original dataset;
(j) modify the at least one synthetic dataset based on the comparison;
and
(k) repeat procedures (d)-(g) until the comparison of the first results to the second results is less than a particular threshold.

14 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/825,040Filed 20 Mar 2020 · continuation
Priority: 6 Jul 2018
Published: US 2020/0012891 A19 Jul 2020
Granted: 12 Jul 2022
Term ends: Not estimatedThe source records don’t support an estimate.

Classification102 codes

G06F 9/541
Interprogram communication: via adapters, e.g. between incompatible applications
G06F 8/71
Software maintenance or management: version control ; Configuration management
G06F 9/54
Multiprogramming arrangements: interprogram communication
G06F 9/547
Interprogram communication: remote procedure calls [RPC]; Web services

Family

Application62/694,968Us provisional application · filed 6 Jul 2018
Application16/152,072Parent of this continuation · filed 4 Oct 2018
US 2020/0218638 A1Pre-grant publication · published 9 Jul 2020
US 10,635,939 B2Parent of this continuation
US 2020/0012891 A1Published application
US 11,385,943 B2This patent

From the US filing history. Foreign family members aren’t listed.