Anomalous behavior detection
AssigneeH2O.ai Inc.
InventorAshrith Barthur
Life of this patent
Estimating the term…
Abstract
A training dataset is used to train an unsupervised machine learning trained model. Corresponding gradient values are determined for a plurality of entries included in the training dataset using the trained unsupervised machine learning model. A first subset of the training dataset is selected based on the determined corresponding gradient values and a first threshold value selected from a set of threshold values. A labeled version of the selected first subset is used to train a first supervised machine learning model to detect one or more anomalies.
Claims21
(canceled)
A method, comprising:
- receiving event data associated with one or more events;
- inputting features and corresponding feature values associated with the event data to a machine learning model selected from a plurality of machine learning models, wherein the selected machine learning model is a trained supervised model that was trained based on an output of a trained unsupervised machine learning model;
- outputting one or more prediction labels;
- and
- providing a notification that includes one or more remediation measures.
A system, comprising:
- a processor configured to:
- receive event data associated with one or more events;
- input features and corresponding feature values associated with the event data to a machine learning model selected from a plurality of machine learning models, wherein the selected machine learning model is a trained supervised model that was trained based on an output of a trained unsupervised machine learning model;
- output one or more prediction labels;
- and
- provide a notification that includes one or more remediation measures;
- and
- a memory coupled to the processor and configured to provide the processor with instructions.
A computer program product for detecting anomalous behavior, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:
- receiving event data associated with one or more events;
- inputting features and corresponding feature values associated with the event data to a machine learning model selected from a plurality of machine learning models, wherein the selected machine learning model is a trained supervised model that was trained based on an output of a trained unsupervised machine learning model;
- outputting one or more prediction labels;
- and
- providing a notification that includes one or more remediation measures.
Dependencies are inferred from the claim text.