Predictive Artificial Intelligence for Determining Security Events and Mitigation Strategies
AssigneeBank of America Corporation
InventorsPaul Mattison, Matthew Williams, Jennifer Raley, Richard Brown, Amy Abreu
Life of this patent
Estimating the term…
Abstract
Predictive analysis for potential future security events may be performed using machine learning and an artificial intelligence model. Machine learning may be based on historical security event data, and analyzed on micro and macro levels to determine possible future events and a likelihood that those future events may occur. Further, machine learning and artificial intelligence models may be used to determine mitigation strategies to address possible future events.
Claims20
A method for predictive analysis of unauthorized activity, comprising:
- generating, by a predictive analysis computing device, a predictive AI model for predicting future unauthorized activity involving one or more electronic devices based on a data set including historical unauthorized activity events, the data set including a plurality of events, identification of a time at which each event occurred, and a location of each event;
- executing, by the predictive analysis computing device, a first network crawler configured to navigate to one or more computer network sites providing news articles, the first network crawler further configured to identify news articles including one or more key words;
- processing, by the predictive analysis computing device, the identified news articles through the predictive AI model to determine a predicted future event involving unauthorized activity, the predicted future event including a type of unauthorized activity, a time of the unauthorized activity, and a location of the unauthorized activity, wherein the predictive AI model is configured to:
- identify one or more trends in the data set including historical unauthorized activity events;
- determine one or more possible future events;
- determine a probability for each of the one or more possible future events based on the identified one or more trends;
- determining, by the predictive analysis computing device, a mitigation activity for the predicted future event;
- and
- transmitting, by the predictive analysis computing device, a notification of the mitigation activity to a mitigation system for implementation.
An apparatus comprising:
- a processor;
- and
- memory storing computer-readable instructions that, when executed by the processor, cause the apparatus to:
- generate a predictive AI model for predicting future unauthorized activity involving one or more electronic devices based on a data set including historical unauthorized activity events, the data set including a plurality of events, identification of a time at which each event occurred, a type of each event, and a location of each event;
- execute a first network crawler configured to navigate to one or more websites providing news articles, the first network crawler further configured to identify news articles including one or more key words relating to unauthorized activity;
- process the identified news articles through the predictive AI model to determine a predicted future event involving unauthorized activity, the predicted future event including a type of unauthorized activity, a time of the unauthorized activity, and a location of the unauthorized activity, wherein the predictive AI model is configured to:
- identify one or more trends in the data set including historical unauthorized activity events;
- determine one or more possible future events;
- determine a probability for each of the one or more possible future events based on the identified one or more trends;
- determine a mitigation activity for the predicted future event;
- and
- transmit a notification of the mitigation activity to a mitigation system for implementation.
A non-transitory computer-readable medium storing computer-readable instructions that, when executed by a processor, cause a predictive analysis apparatus to:
- generate a predictive AI model for predicting future unauthorized activity involving one or more electronic devices based on a data set including historical unauthorized activity events, the data set including a plurality of events, identification of a time at which each event occurred, a type of each event, and a location of each event;
- execute a first network crawler configured to navigate to one or more websites providing news articles, the first network crawler further configured to identify news articles including one or more key words relating to unauthorized activity;
- process the identified news articles through the predictive AI model to determine a predicted future event involving unauthorized activity, the predicted future event including a type of unauthorized activity, a time of the unauthorized activity, and a location of the unauthorized activity, wherein the predictive AI model is configured to:
- identify one or more trends in the data set including historical unauthorized activity events;
- determine one or more possible future events;
- determine a probability for each of the one or more possible future events based on the identified one or more trends;
- determine a mitigation activity for the predicted future event;
- and
- transmit a notification of the mitigation activity to a mitigation system for implementation.
Dependencies are inferred from the claim text.