International Business Machines Corporation

Rajesh Phillips

Ritesh Kumar Gupta

Sumit Kumar

Raghavendra Rao Dhayapule

Vijay Ekambaram

Puneet Sharma

Rajendra Rao

Manisha Sharma Kohli

Methods, systems and computer program products for providing automatic determination of recommended hyper-local data sources and features for use in modeling is provided. Responsive to training each model of a plurality of models, aspects include receiving client data, a use-case description and a selection of hyper-local data sources, generating a client data profile, determining feature importance and generating a use-case profile. Aspects also include generating a feature profile relation graph including client data profile nodes, hyper-local feature nodes and a use-case profile nodes, wherein each hyper-local feature node is associated with one or more client data profile nodes and user-case profile nodes by a respective edge having an associated edge weight. Responsive to receiving a new client data set and a new use-case description, aspects also include determining one or more hyper-local features as suggested hyper-local features for use in building a new model.

Automatic determination of suitable hyper-local data sources and features for modeling

A computer implemented system and method provide for a transfer learning platform system. The method provides an introduced enterprise security policy (IESP) to a first enterprise system. During a threat, the IESP is toggled on and off. A first change element is determined that represents a change in a logging system of the first enterprise between a first and second log element of the first enterprise captured when the IESP was toggled on and off, respectively. The IESP is provided to a second enterprise system. A second change element is determined that represents a change in a logging system of the second enterprise between a first log element of the second enterprise. The method further determines that the first and second change element are different, and, conditioned upon the determining that the second change element is different than the first change element, removes the IESP from the second enterprise system.

Transfer learning platform for improved mobile enterprise security

Methods, systems and computer program products for facilitating use of select hyper-local data sets for improved modeling are provided. Aspects include receiving customer data associated with a customer by a workbench platform and determining an accuracy of a customer model using the customer data. For each of a plurality of hyper-local data sets, aspects also include determining an increase in model accuracy based on use of the hyper-local data set and the customer data. Aspects include identifying at least one group of hyper-local data sets of the plurality of hyper-local data sets that result in similar increases in model accuracy. Aspects also include facilitating use of a selected one or more of the hyper-local data sets of the at least one group of hyper-local data sets in generating an improved accuracy customer model.

Facilitating use of select hyper-local data sets for improved modeling

A method for testing an extract, transform, load job (ETL job) is provided. The method may include receiving an uploaded ETL job. The method may also include executing a functionality test of the uploaded ETL job using a test bucket. The method may further include determining the executed functionality test produces a failure result. The method may also include creating at least one test sub-job corresponding to at least one stage within on the uploaded ETL job. The method may further include generating a plurality of test data for each of the at least one created test sub-job. The method may also include executing the at least one created test sub-job using the plurality of generated test data. The method may further include creating a report based on a plurality of results associated with the at least one executed test sub-job.

Automating extract, transform, and load job testing

Compiling test cases. The method may include uploading at least one extract, transform, load job (ETL job) and a plurality of test cases. The method may also include identifying a plurality of design features associated with the at least one uploaded ETL job. The method may further include identifying at least one feature change within the plurality of identified design features. The method may also include determining a plurality of related test cases within the plurality of uploaded test cases corresponding to the at least one identified feature change. The method may further include creating a test bucket based on a grouping of the determined plurality of related test cases. The method may also include adding at least one of a plurality of corresponding ETL jobs and a plurality of corresponding ETL job stages associated with the at least one identified feature change to the created test bucket.

Growing community of inventors

Bengaluru, India

Rajesh Phillips