International Business Machines Corporation

Thomas T Hanis

Eoin Lane

Bruce Henry Hyre

Jessica G Snyder

Donnie Allen Smith, Jr

Zhuo Zhao

Jessica G Smith

Ke Zhang

Peter Alan Coldicott

Subhendu Das

Yi-Hui Ma

Kenneth L Greenlee

Shanna Hayes

Sunil Kumar Mishra

Paul J Seifert

Fang Lu

Claus T Jensen

Azadeh Salehi

Alphonse Joseph Wojtas

John Kenneth Senegal

Frederick William Rowe

Vijay Kumar Bhadriraju

Data synchronization includes receiving an update request from a client system for a first record set, wherein the update request includes search criteria used to initially determine the first record set and hash summaries of records of the first record set, and searching a data storage device for records matching the search criteria. The searching generates a second record set of records having hash summaries. Record identifiers of records of the second record set may be compared with record identifiers of the hash summaries of the first record set. Responsive to determining that a record identifier of a selected hash summary of the first record set matches a record identifier of a record of the second record set, a determination may be made whether hash fields of the selected hash summaries mismatch and, responsive to determining a mismatch between hash fields, a field of the record of the second record set represented by the mismatched hash fields may be sent to the client system without sending fields of record determined to match.

Record property synchronization in a network computing system

The disclosed embodiments include a method for performing financial fraud assessment that includes creating a machine learning model based on features used to identify financial fraud risk; receiving financial information associated with customer accounts; establishing communities for the customer accounts; creating a baseline set of the features for each of the communities; receiving new financial information associated with customer accounts; updating the communities for the customer accounts based on the new financial information; extracting an updated set of the features for each of the communities; and determining a difference between the baseline set of the features and the updated set of the features for each of the communities; and using the machine learning model to determine financial fraud risk for each of the communities based on the difference between the baseline set of the features and the updated set of the features for each of the communities.

Fraud detection based on community change analysis using a machine learning model

A computer-implemented method for performing financial fraud assessment, the method includes receiving financial information associated with customer accounts that have been identified as being associated with suspicious financial activity; establishing communities for the customer accounts; creating a baseline set of features for each of the communities; receiving new financial information associated with customer accounts; updating the communities for the customer accounts based on the new financial information; extracting an updated set of features for each of the communities; and performing fraud assessment by determining whether a change between the updated set of features and the baseline set of features for each of the communities is indicative of an increased risk of fraud.

Fraud detection based on community change analysis

An example operation may include one or more of a computer storing a first set of received data analytics in a blockchain, the first set associated with a subject matter. The operation further comprises the one or more computer storing a second set of received data analytics in the blockchain, the second set associated with the subject matter. The operation further comprises the one or more computer deriving and storing in the blockchain a first set of metrics based on analysis of the first set of analytics processed with the second set of analytics. The operation further comprises the one or more computer storing a third set of received data analytics in the blockchain, the third set associated with the subject matter, and deriving and storing a second set of metrics based on analysis of the first set of metrics processed with the third set of data analytics.

Collaborative analytics for fraud detection through a shared public ledger

Operational data in a distributed processing system is managed by monitoring a workload of the system to establish a current assessment of operational data movement between data sources and data targets, receiving historical information on previous data movement including previous instances of movement resulting in a compromise of one or more quality-of-service criteria, determining from the current assessment and historical information that upcoming operational data actions will not meet a particular quality-of-service criterion, and responsively applying a data management optimization infrastructure (data backplane services) adapted to advance the particular quality-of-service criterion according to definitions for the data sources and data targets. The operational outcome is predicted using a cognitive system trained with historical information including historical operational factors correlated with historical operational outcomes relative to the quality-of-service criteria.

Automated operational data management dictated by quality of service criteria

Machine learning to predict quality-of-service needs in an operational data management system

An example operation may include one or more of a computer deriving a first set of metrics from processing a first and second set of data analytics, the sets associated with a subject matter. The operation further comprises the one or more computer deriving a second set of metrics from processing a third and fourth sets of data analytics, the third and fourth sets associated with the subject matter. The operation further comprises the one or more computer publishing the first and second set of metrics. The operation further comprises the one or more computer receiving a first plurality of requests for processing of analytics using the first set of metrics. The operation further comprises the one or more computer receiving a second plurality of requests for processing of analytics using the second set of metrics. The operation further comprises the one or more computer maintaining tallies of the requests.

A blockchain function may include one or more of receiving a last observed location identifier for a product identified via a product tag associated with the product, determining whether the last observed location identifier was received from a trusted source device, and storing the last observed location identifier in a blockchain with a confirmed status responsive to determining the last observed location identifier was received from the trusted source device.

Tracking objects using a trusted ledger

A blockchain of transactions may be referenced for various purposes and may be later accessed by interested parties for ledger verification. One example method of operation may include reading a tag affixed to an asset, transmitting a request to update an asset status of the asset in a blockchain, receiving validation confirmation based on content of the request, and updating the asset status of the asset in the blockchain.

Tracking assets with a blockchain

Associating a state machine with an asset for impact analysis by creating an asset-and-event topic map meta-model that identifies assets and events in a topic map based index with instance ontology based on a topic map meta model that identifies assets and a topic map meta-model that identifies events; creating a state topic map meta-model representing operating states of at least one asset; and associating an asset of the asset-and-event topic map meta-model with operating states of the asset in the state topic map meta-model.

Semantic mapping of topic map meta-models identifying assets and events to include modeled reactive actions

A method, system and computer-usable medium are disclosed for efficient searching of a semantic model of resources and resource relationships. A query is received from an application. In turn the query is processed to determine an application usage classification for the application, which is then used to reference an index of subsets of the semantic model to identify a subset of the semantic model associated with the application usage classification. The identified subset of the semantic model is then used to modify the query, which is then used as a modified query to query the semantic model. In response, a sub-graph of the semantic model corresponding to the subset of the semantic mode is received, which in turn is provided to the application.

Model navigation constrained by classification

Tracking a tagged object may include receiving, using a first processor, a first video of an object tagged with a radio frequency identification (RFID) tag and first metadata read from the RFID tag. The first metadata may be stored in association with the first video using the first processor. First updated metadata may be written to the RFID tag using the first processor. The first updated metadata may specify at least one of a time the first video is received or a location of the first processor.

Growing community of inventors

Raleigh, NC, United States of America

Thomas T Hanis