Accenture Global Solutions Limited

Sas Institute Inc.

Vijay Desai

Revathi Subramanian

Kun Qiu

Qiang Song

Madhan Kumar Srinivasan

Guruprasad Pv

Arun Purushothaman

Paul Charles Dulany

Michael S Eisenstein

Brian Lee Duke

Lizhong Wu

Daniel Marcus Lombardo

Bryan Johns

Paul Boynton

Laser Seymour Kaplan

Ravi Prakash

Hongrui Gong

Kannan Shashank Shah

Ho Ming Luk

Mythili Krishnan

Kunal Bhowmick

Kevin Chaowen Chen

Narayanaswamy Thimmappa

Mriga Bansal

Suraj Thulkar

William Szczuka

Andrew Engel

Daniel J Dotson

Terrance Gordon Barker

Durga Kalyan Ganjapu

Ashok Rajaraman

An Artificial Intelligence (AI) based document processing and validation system identifies anomalies such as errors, fraud, and duplicates of received documents and enables automatic actions for valid documents using machine learning (ML) techniques. The received documents are processed for determining probabilities for errors, fraud, and duplicates. A validation worklist is generated with the documents arranged in descending order of the probabilities and invalid documents with higher probabilities are flagged for review while the valid documents with lower probabilities are further processed for the execution of automatic actions. The feedback from the invalid document review is used to further train the models in determining the probabilities.

Artificial intelligence (AI) based document processing and validation

A device receives historical data associated with multiple cloud computing environments, trains one or more machine learning models, with the historical data, to generate trained machine learning models that generate outputs, and trains a model with the outputs to generate a trained model. The device receives particular data, associated with a cloud computing environment, that includes data identifying usage of resources associated with the cloud computing environment, and processes the particular data, with the trained machine learning models, to generate anomaly scores indicating anomalous usage of the resources associated with the cloud computing environment. The device processes the one or more anomaly scores, with the trained model, to generate a final anomaly score indicating anomalous usage of at least one of the resources associated with the cloud computing environment, and performs one or more actions based on the final anomaly score.

Utilizing machine learning models to process resource usage data and to determine anomalous usage of resources

A device may receive historical cloud data associated with resources of a cloud computing environment, and may receive historical customer data associated with requested resource usage by customers of the cloud computing environment. The device may determine a usage growth profile based on the historical cloud data and the historical customer data, and may determine, based on the historical cloud data and the historical customer data, usage deviation data indicating deviations between actual and planned resource usage. The device may train a model, with the usage growth profile and the usage deviation data, to generate a trained model, and may receive a request for new resource usage by a customer associated with the cloud computing environment. The device may process the request for the new resource usage, with the trained model, to generate projected resource usage data, and may perform actions based on the projected resource usage data.

Utilizing a machine learning model to predict a quantity of cloud resources to allocate to a customer

A multi-layer compute sizing correction stack may generate prescriptive compute sizing correction tokens for controlling sizing adjustments for computing resources. The input layer of the compute sizing correction stack may generate cleansed utilization data based on historical utilization data received via network connection. A prescriptive engine layer may generate a compute sizing correction trajectory detailing adjustments to sizing for the computing resources. Based on the compute sizing correction trajectory, the prescriptive engine layer may generate the compute sizing correction tokens that that may be used to control compute sizing adjustments prescriptively.

Prescriptive analytics based compute sizing correction stack for cloud computing resource scheduling

A device may receive a computing resource request. The computing resource request may be related to allocating computing resources for a job. The device may process the computing resource request to identify a set of parameters related to the computing resource request or to the job. The set of parameters may be used to determine an allocation of the computing resources for the job. The device may utilize multiple machine learning models to process data related to the set of parameters identified in the computing resource request. The device may determine the allocation of the computing resources for the job based on utilizing the multiple machine learning models to process the data. The device may generate a set of scripts related to causing the computing resources to be allocated for the job according to the allocation. The device may perform a set of actions based on the set of scripts.

Determining an allocation of computing resources for a job

A device may receive data related to operations of a plurality of managed devices. The device may determine, after receiving the data, a multi-entity profile for the data. The device may determine, using the multi-entity profile, a set of sub-models for the data after determining the multi-entity profile. The set of sub-models may be associated with processing the data in a contextualized manner. The device may generate a model based on the set of sub-models. The device may perform one or more actions related to the plurality of managed devices or the at least one alert based on respective scores associated with the plurality of managed devices after generating the model.

Analyzing device-related data to generate and/or suppress device-related alerts

Data from an application is analyzed periodically in real-time using a predictive data model to predict potential application failures. Application logs are used to build the predictive data model. The predictive data model includes features created from the application logs which are good predictors of application failures. The predictive data model analyzes and provides anomaly scores for various anomalies for the real-time data collected over a time period. The anomaly scores are compared with a threshold score to predict the probability of occurrences of application failures. If there is a higher probability of occurrence of an incident of application failure, corrective actions to mitigate or reduce the probability of occurrence of the application failure are implemented.

Application monitoring and failure prediction

This disclosure describes methods, systems, and computer-program products for determining classification rules to use within a fraud detection system The classification rules are determined by accessing distributional data representing a distribution of historical transactional events over a multivariate observational sample space defined with respect to multiple transactional variables. Each of the transactional events is represented by data with respect to each of the variables, and the distributional data is organized with respect to multi-dimensional subspaces of the sample space. A classification rule that references at least one of the subspaces is accessed, and the rule is modified using local optimization applied using the distributional data. A pending transaction is classified based on the modified classification rule and the transactional data.

Rule optimization for classification and detection

Systems and methods are provided for operation upon data processing devices are provided for operating with a fraud detection system. As an example, a system and method can be configured for receiving, throughout a current day in real-time or near real-time, financial transaction data representative of financial transactions initiated by different entities. At multiple times throughout the day, a summarization of the financial transaction data (which has been received within a time period within the current day) is generated. The generated summarization is used to determine whether fraud has occurred with respect to a financial transaction contained in the received authorization data or with respect to a subsequently occurring financial transaction.

Computer-implemented multiple entity dynamic summarization systems and methods

Systems and methods are provided for estimating a value for a target variable. A plurality of known entities are assigned to cells of a grid, where the known entities are assigned to the cells based upon attribute data. A determination is made as to whether each cell has at least a threshold number of assigned known entities. When one of the cells contains fewer than the threshold number of known entities, cells are combined to form a super cell. A model is generated for each cell and super cell based upon target variable values for known entities assigned to that cell or super cell. Data for a target entity is received, and the target entity is assigned to one the cells. One of the models is selected based upon the cell assignment, and an estimate is generated for the target variable for the target entity using the selected model.

Computer-implemented systems and methods for forecasting and estimation using grid regression

Computer-implemented systems and methods for determining a subset of unknown targets to investigate. For example, a method can be configured to receive a target data set, wherein the target data set includes known targets and unknown targets. A supervised model such as a neural network model is generated using the known targets. The unknown targets are used with the neural network model to generate values for the unknown targets. Analysis with an unsupervised model is performed using the target data set in order to determine which of the unknown targets are outliers. A comparison of list of outlier unknown targets is performed with the values for the unknown targets that were generated by the neural network model. The subset of unknown targets to investigate is determined based upon the comparison.

Computer-implemented semi-supervised learning systems and methods

Computer-implemented systems and methods for determining one or more actions to be taken with respect to a first entity. A computer-implemented method can be configured to receive data that is related to characteristics of the first entity as well as data that is related to a plurality of segments. Assignments are determined between the first entity and the segments based upon the characteristics of the first entity and the characteristics associated with the segments. A determined assignment includes a membership probability that is indicative of how probable is membership of the first entity with respect to a segment. One or more actions are determined for the first entity based upon the membership probabilities and action information associated with the assigned segments.

Computer-implemented clustering systems and methods for action determination

Computer-implemented systems and methods for analyzing activities associated with accesses of a computer network. A computer-implemented method can be configured to receive data related to the activities associated with the accesses of a computer network. The network activities data are segmented into a plurality of network activities segments. For each of the network activities segments, an anomaly detection predictive model is generated. The generated predictive models are for use in analyzing the activities associated with the computer network.

Growing community of inventors

San Diego, CA, United States of America

Vijay Desai