Capital One Services, LLC

Max Miracolo

Joshua S Edwards

Cruz Vargas

Phoebe Atkins

Alexander Lin

Lin Ni Lisa Cheng

Brian McClanahan

Michael Saia

Kaylyn S Gibilterra

Tyler Maiman

Jacob Learned

Michael Bakr Mossoba

Abdelkader M'Hamed Benkreira

Rajko Ilincic

Robert T Perry

Kyle Rankin Johnson

Austen Novis

Mia Rodriguez

Natasha Mitchko

Abdelkader Benkreira

Louis Buell

Systems and methods for identifying and remedying password insecurities are disclosed. The systems and methods include crawling websites to identify popular cultural terms and saving the cultural terms in a backend system. The cultural terms can include names of celebrities, politicians, movies, and the like. An identification system receives a password and compares the received password to the cultural terms using a similarity score. If the number of similarities is above a predetermined threshold, or if the number of differences is below a predetermined threshold, the identification system denies the password. A recommendation system can generate a suggested password, which can also be compared to the cultural terms. The systems and methods also provide the ability to calculate a similarity score if the cultural terms or passwords are saved in an encrypted or hashed format.

Systems and methods for providing secure passwords

Systems and methods of the present disclosure enable database search. The systems and/or methods may include receiving a search query that includes an input document having text. Word embeddings are generated within the input document, where the word embeddings include vector representations of words in the text of the input document. An average input document word embedding vector is determined for the word embeddings of the input document. A set of stored documents is accessed, where each stored document includes a stored text has a particular average stored document word embedding vector. A similarity model is used to determine a similarity metric measuring the similarity between the input document and each stored document based on the average input document word embedding vector and the particular average stored document word embedding vector of each stored document.

Systems for database searching and database schemas management and methods of use thereof

Methods and systems disclosed herein describe customizing searching. Search queries may be customized according to a user's preferences. A user may emphasize or indicate that additional weight should be given to one or more terms in a search query. Terms that are weighted higher may have a larger impact on the results that are returned in response to the search query. In addition to changing the terms in a search query, a user may provide a weight for each term. Each term in a search query may be weighted to varying degrees, giving a user more control over the results that are returned. The weights may be used with machine learning techniques to generate a vector representation of a search query. The vector representation of the search query may be compared with vector representations of search objects to determine results that match the search query.

Customizing search queries for informational retrieval

A computer-implemented method for anonymizing online transaction details may include performing a process to generate an identifier (ID) and reference address for a user, and receiving a request for transaction processing from an e-commerce server. The request may include first data including: information associated with a purchase of a product to be delivered to the user; the identifier; and the reference address. The method may further include: in response to the request, determining whether the ID and reference address are included in the request, and if so, obtaining the accurate address and shipping rate rules; applying, based on the first data and the accurate address, the shipping rate rules to determine accurate shipping rate cost information associated with delivering the product to the accurate address; performing an anonymizing process on the accurate information to obtain anonymous shipping rate information, and transmitting the anonymous shipping rate information to the e-commerce server.

System and method for obfuscating transaction information

Disclosed herein are system, method, and device embodiments for implementing password suggestion. An embodiment operates by selecting one or more random terms from dictionary information, generating an alphanumeric string based on a password requirement, combining the one or more random terms and the alphanumeric string to form a generated password, determining a password strength of the generated password based on compromised password information, and presenting the generated password for selection by a user device when the password strength meets or exceeds a threshold value.

Automated password generation

A processor may receive data and generate a quantified representation of the data by processing the data using at least one machine learning (ML) algorithm, the quantified representation of the data indicating a sentiment of content of the data. The processor may automatically revise the content of the communications data. The revising may include determining a reaction to the content of the communications data, generating a quantified representation of the reaction, determining a difference between the quantified representation of the reaction and the quantified representation of the communications data, identifying, based on the difference, a portion of the content having an unintended sentiment, and replacing the portion of the content with different content.

Feedback control for automated messaging adjustments

In some implementations, a credit decision platform may receive a credit request from an applicant and obtain domestic historical data associated with the applicant from a credit bureau device. The credit decision platform may obtain access to an email account associated with the applicant based on determining that the domestic historical data associated with the applicant is insufficient to process the credit request. The credit decision platform may identify, using one or more machine learning models, a set of email messages included in the email account that are relevant to the credit request and may analyze content included in the set of email messages to generate non-domestic historical data associated with the applicant. The credit decision platform may generate a decision on the credit request based on an estimated creditworthiness of the applicant, which may be determined based on the non-domestic historical data.

Using email history to estimate creditworthiness for applicants having insufficient credit history

Customizing search queries for information retrieval

A device receives, from a transaction device, transaction data associated with a transaction of a user logged into the transaction device, and receives information indicating a selection of an abort transaction mechanism to cause the transaction to be canceled concurrently with the user being logged out of the transaction device. The device provides, to a user device associated with the user, a notification indicating that the transaction was canceled and that the user was logged out, and determines whether a response, indicating that the notification was received by the user and indicating a reason for utilizing the abort transaction mechanism, is received from the user device within a threshold period of time. The device provides an alert message to an emergency point of contact for the user when it is determined that the response is not received from the user device within the threshold period of time.

Utilizing a machine learning model to perform actions based on selection of a single selection abort transaction mechanism

Disclosed are systems and methods for data breach identification. The method may include: generating virtual card number (VCN) data sets; storing the VCN data sets on a first database; receiving one or more compromised VCN data sets stored on a second database and obtained from a scan of unindexed websites; comparing the compromised VCN data sets with the VCN data set stored on the first database to determine whether the VCN data sets have been compromised; for each compromised VCN data set, training the recurrent neural network (RNN) to associate the compromised VCN data sets with one or more sequential patterns found within the compromised VCN data sets to generate a trained RNN; receiving a first VCN data set from the first database; determining whether the first VCN data set matches a compromised VCN data set; and transmitting a message indicating the determination to a user or provider device.

Growing community of inventors

Brooklyn, NY, United States of America

Max Miracolo