System and methods for data model detection and surveillance
AssigneeNasdaq, Inc.
InventorsXuyang Lin, Tudor Morosan, Douglas Hamilton, Shihui Chen, Hyunsoo Jeong, Jonathan Rivers, Leonid Rosenfeld
Life of this patent
Estimating the term…
Abstract
A computer system is provided for monitoring and detecting changes in a data generating processes, which may be under a multi-dimensional and unsupervised setting. A target dataset is split into paired subgroups by a separator and one or more detectors are applied to detect changes, anomalies, inconsistencies, and the like between the paired subgroups. Metrics may be generated by the detector(s), which are then passed to an evaluating system.
Claims20
A computer system for detecting changes within datasets supplied from external data sources, the computer system comprising:
- a processing system that includes at least one processor, the processing system configured to perform operations comprising:
- obtaining at least a first dataset and a second dataset that have been generated by at least one external computer system;
- executing a plurality of different detector processes against the first dataset and the second dataset, wherein the plurality of different detector processes each use different processing for the first and second datasets and each generate, as a result of the executing, at least one metric,
- wherein the plurality of different detector processes includes a generative adversarial network (GAN) detector process that includes:
- training, using a generative neural network, a discriminative neural network by using the first data set, and
- using the trained discriminative neural network to measure a level of difference between the first dataset and the second dataset;
- performing a comparison using the at least one metric generated from each of the plurality of different detector processes to at least one threshold value;
- and
- determining, based on the performed comparison, whether that a statistically significant change has occurred between the first dataset and the second dataset.
A method of detecting changes in data provided from an external computer system, the method comprising:
- obtaining at least a first dataset and a second dataset that have been generated by at least one external computer system;
- executing a plurality of different detector processes against the first dataset and the second dataset, wherein the plurality of different detector processes each use different processing for the first and second datasets and each generate, as a result of the executing, at least one metric,
- wherein the plurality of different detector processes includes a generative adversarial network (GAN) detector process that includes:
- training, using a generative neural network, a discriminative neural network by using the first data set, and
- using the trained discriminative neural network to measure a level of difference between the first dataset and the second dataset;
- performing a comparison using the at least one metric generated from each of the plurality of different detector processes to at least one threshold value;
- and
- determining, based on the performed comparison, that a statistically significant change has occurred between the first dataset and the second dataset.
A non-transitory computer readable storage medium storing a computer program for use with a computer system, the computer program comprising instructions that, when executed by the computer system, cause the computer system to perform operations comprising:
- obtaining at least a first dataset and a second dataset that have been generated by at least one external computer system;
- executing a plurality of different detector processes against the first dataset and the second dataset, wherein the plurality of different detector processes each use different processing for the first and second datasets and each generate, as a result of the executing, at least one metric,
- wherein the plurality of different detector processes includes a generative adversarial network (GAN) detector process that includes:
- training, using a generative neural network, a discriminative neural network by using the first data set, and
- using the trained discriminative neural network to measure a level of difference between the first dataset and the second dataset;
- performing a comparison using the at least one metric generated from each of the plurality of different detector processes to at least one threshold value;
- and
- determining, based on the performed comparison, that a statistically significant change has occurred between the first dataset and the second dataset.
Dependencies are inferred from the claim text.