-
公开(公告)号：US20210174562A1
公开(公告)日：2021-06-10
申请号：US16706518
申请日：2019-12-06
Applicant: BANK OF AMERICA CORPORATION
Inventor： Eren Kursun
Abstract: A system for feature relevance visualization optimization is provided. The system comprises a controller configured for modifying placement of features in a relevance visualization. The controller is further configured to: receive interaction data comprising one or more features positioned in the relevance visualization, wherein the one or more features are defined and measurable properties of the interaction data; construct a logical grouping of the one or more features based on a type of each of the one or more features, wherein similar features are collocated in the relevance visualization; construct a machine learning-based grouping of the one or more features based on relevance calculations for the one or more features; combine the logical grouping and the machine learning-based grouping to generate a combined feature placement, wherein the one or more features are repositioned in the relevance visualization; and output the relevance visualization having the combined feature placement.
-
公开(公告)号：US20210049456A1
公开(公告)日：2021-02-18
申请号：US16537884
申请日：2019-08-12
Applicant: BANK OF AMERICA CORPORATION
Inventor： Eren Kursun
Abstract: Embodiments of the present invention provide an improvement to conventional machine model training techniques by providing an innovative system, method and computer program product for the generation of synthetic data using an iterative process that incorporates multiple machine learning models and neural network approaches. A collaborative system for receiving data and continuously analyzing the data to determine emerging patterns is provided. The proposed invention involves generating synthetic data clusters to be stored and used for retraining the main model as well as other models. In addition, the invention includes using one or more (subset) of the synthetic data clusters to train or retrain machine learning models, developing and training machine learning models that are trained with emerging synthetic data clusters, and ensembling machine learning models trained with emerging synthetic data clusters.
-
公开(公告)号：US20210042420A1
公开(公告)日：2021-02-11
申请号：US16531603
申请日：2019-08-05
Applicant: Bank of America Corporation
Inventor： Eren Kursun
Abstract: A system for integrated natural language programming (“NLP”) and event analysis provides threat detection in computing systems. In particular, the system may use an NLP unit to analyze threat logs from various sources according to multiple different metrics and/or analysis paradigms. Upon completing the analysis, the system may extract, via machine learning, event and/or threat patterns which may be integrated into the system's threat detection processes.
-
公开(公告)号：US20210041855A1
公开(公告)日：2021-02-11
申请号：US16532796
申请日：2019-08-06
Applicant: Bank of America Corporation
Inventor： Eren Kursun
IPC: G05B19/4155 , G06N20/00
Abstract: Systems, computer program products, and methods are described herein for a centralized resource transfer engine for facilitating resource transfers between distributed IoT devices. The present invention is configured to receive, from a first autonomous IoT device, a transaction authorization request to execute a transaction with a second autonomous IoT device; receive information associated with the first autonomous IoT device, information associated with the second autonomous IoT device, and information associated with the transaction; determine one or more constraints associated with the transaction; determine that the first autonomous IoT device is authorized to execute the transaction with the second autonomous IoT device within the one or more constraints; transmit a transaction authorization to the first autonomous IoT device to execute the transaction within the one or more constraints; and receive, from the first autonomous IoT device, an indication that the transaction has been executed.
-
公开(公告)号：US10855666B2
公开(公告)日：2020-12-01
申请号：US15995894
申请日：2018-06-01
Applicant: BANK OF AMERICA CORPORATION
Inventor： Dharmender Kumar Satija , Eren Kursun
Abstract: The invention relates to providing alternate user communication based on user identification. A communication from a user may be received, and the communication may include an authentication credential from the user. When the user is determined to be an unauthorized user based on the authentication credential, the communication may be extended in order to capture more information from the unauthorized user, and to deter the unauthorized user from making other unauthorized access attempts. In addition to the extension of the communication with the unauthorized user, one or more additional alternate treatments may be presented to the unauthorized user in order to identify, track, and/or prevent access by the unauthorized user.
-
Patent Agency Ranking
公开(公告)号：US20200186523A1
公开(公告)日：2020-06-11
申请号：US16211405
申请日：2018-12-06
Applicant: Bank of America Corporation
Inventor： Eren Kursun , Neil David Zane
Abstract: The present disclosure is directed to a novel system for using unique device and user identifiers to perform authentication of a user, device, and/or transaction. In particular, the system may use device biometric profiles and/or user identifiers to generate a unique identifiable signature for each user and/or device. The unique signature may then be used to authenticate devices as well as transactions submitted by said devices. In this way, the system increases the security of device authentication by helping to prevent the use of device hijacking methods that exploit conventional authentication practices.
-
公开(公告)号：US20200184326A1
公开(公告)日：2020-06-11
申请号：US16210584
申请日：2018-12-05
Applicant: BANK OF AMERICA CORPORATION
Inventor： Eren Kursun , William David Kahn
Abstract: Systems, computer program products, and methods are described herein for de-conflicting data labeling in real-time deep learning systems. The present invention is configured to retrieve one or more dynamically generated expert profiles; and determine an optimal expert mix of experts to classify the transaction into a transaction types, wherein the expert profiles comprises: (i) shared information metrics, (ii) divergence metrics, (iii) characteristics associated with the one or more experts, (iv) a predictive accuracy of the one or more experts, (v) an exposure score associated with the one or more experts, and (vi) information associated with the transaction, wherein the optimal expert mix comprises: (i) a best expert for classifying the transaction, (ii) a combination score from at least the portion of the one or more experts evaluating the transaction simultaneously, and (iii) a sequence of at least the portion of the one or more experts analyzing the transaction.
-
38.发明申请公开(公告)号：US20200184053A1
公开(公告)日：2020-06-11
申请号：US16210427
申请日：2018-12-05
Applicant: Bank of America Corporation
Inventor： Eren Kursun
IPC: G06F21/32 , G06F21/57 , G06K9/00 , G06F16/9535 , G06N3/08
Abstract: Embodiments of the present invention provide a system for generative adversarial network training and feature extraction for biometric authentication. The system collects electronic biometric data of a user from one or more data sources, and stores the collected electronic biometric data as a biometric user profile for the user in a personal NoSQL database library associated with the user. A generative adversarial neural network system then determines improved biometric feature selection and improved model refinements for existing biometric authentication models based on the biometric profile for the user in the personal library associated with the user. The system can then determine user exposure levels for different authentication channels, including certain biometric authentication channels. A custom adversarial strategy for general adversarial network attacks is then established based on the user exposure levels to generate a biometric authentication process that is more accurate and secure.
-
39.发明申请公开(公告)号：US20200169483A1
公开(公告)日：2020-05-28
申请号：US16200050
申请日：2018-11-26
Applicant: Bank of America Corporation
Inventor： Eren Kursun
Abstract: Embodiments of the present invention provide a system for a pattern-based examination and detection of malfeasance through dynamic graph network flow analysis. The system is typically configured for extracting historical information for a first plurality of resource pools, generating a historical dynamic graph based on the historical information, identifying from the historical information, a historical set of resource distribution events associated with a malfeasance, determining from the historical dynamic graph, at least one historical malfeasance pattern, receiving current resource distribution request information for a second plurality of resource pools, generating a current dynamic graph comprising a current plurality of nodes and a current plurality of edges, monitoring the current dynamic graph and identify a current malfeasance pattern, and executing one or more remediation actions on one or more of the second plurality of resource pools associated with the current dynamic graph.
-
40.发明申请公开(公告)号：US20200167787A1
公开(公告)日：2020-05-28
申请号：US16200077
申请日：2018-11-26
Applicant: Bank of America Corporation
Inventor： Eren Kursun
IPC: G06Q20/40 , G06F16/901 , H04L29/08 , G06N20/10
Abstract: Embodiments of the present invention provide a system for dynamic graph network flow analysis and real time remediation execution. Information for multiple accounts is extracted to generate a plurality of dynamic directed and undirected graphs made up of multiple nodes and edges. The nodes represent at least one of the multiple accounts, and each edge represents at least an association or transfer between two nodes. A custom entropy and divergence value is determined for each pair of nodes linked by an edge, as compared to similar or related nodes and edges. A nodal set of the graphs is identified as having aggregate custom entropy and divergence value that is associated with anomalous directional flow from a first node, across intermediary nodes, to a second node. A remediation action is executed with respect to one or more accounts associated with the nodal set in response to identifying the anomalous directional flow.
-
-
-
-
-
-
-
-
-
Search Results
128
records
(took 0.022 seconds)
