American Express Travel Related Services Company, Inc.

Sandeep Bose

Matthew Kent Meyer

Jeremy David Seideman

Ravi Arasan

Gurusamy Ramasamy

Vinod Yadav

Debasish Das

Marimuthu Ponnambalam

Madhu Sudhan Reddy Gudur

Ravi K Kaushik

Carmen Patricia Argüello

Ambika Aggarwal

Ravneet Ghuman

Roopesh R Varier

Mario Fragoso

Sastry Vsm Durvasula

Arindam Chatterjee

Balaji Balaraman

Mohammad Torkzahrani

Nitish Sharma

Kunal Chandrashekhar Joshi

Himanshu Prabhakar

Curtis T Merryweather

Ravi Varma

Shubham Arora

Manoj Kumar Rana

Ravi Batra

Madhu Sudan Reddy Gudur

Suraj Madnani

Anand Bhushan

Sachin Arya

Karan Anil Kumar

Xiaoyang Chen

Ajay Paul Singh Manesh

Harish R Naik

Purvi Shah

Sanjay S Gwalani

Bhupesh Sharma

Rahul Agarwal

Neha Singh

Anmol Handa

Ajay Kumar Punia

Hui-Ping W Chao

Priya Narayana

Shashank Kapoor

Rahul Panwar

Nikhil Jain

Nivedita Singh

Karina Alvarez

Subhash Godara

Systems and methods for identifying data of interest are disclosed. The system may retrieve unstructured data from an internet data source via an alert system or RSS feed. The system may input the unstructured data into various models and scoring systems to determine whether the data is of interest. The models and scoring systems may be executed in order or in parallel. For example, the system may input the unstructured data into a Naïve Bayes machine learning model, a long short-term memory (LSTM) machine learning model, a named entity recognition (NER) model, a semantic role labeling (SRL) model, a sentiment scoring algorithm, and/or a gradient boosted regression tree (GBRT) machine learning model. Based on determining that the unstructured data is of interest, a data alert may be generated and transmitted for manual review or as part of an automated decisioning process.

Identifying data of interest using machine learning

Systems and methods of the present disclosure may read source data corresponding to a source variable and apply a transformation to the source variable to generate an output variable. Accordingly, one such method comprises receiving a request to access an output variable by applying one or more data transformations to input data; before applying an actual data transformation to the input data, identifying that a match exists with a database of prior data transformations that have been applied to source variables to generate derived variables; identifying that a source variable in the matching one or more data transformations is flagged as sensitive data; and processing the request to access the output variable subject to an access restriction in response to the identification of the source variable that is flagged as sensitive data.

Lineage data for data records

Disclosed are various embodiments for using decision trees for machine-learning when data is missing from a data set. A first attribute for splitting a plurality of records is identified. Then, the plurality of records are split into a first subset of records and a second subset of records. The first subset of records can include each of the plurality of records where a value is present for the first attribute and the second subset of records comprising each of the plurality of records where the value is absent for the first attribute. Finally, a node can be added to a decision tree that reflects the split of the plurality of records into the first subset of records and the second subset of records.

Decision tree learning with missing data

Disclosed are various embodiments for generating relevant notifications of content generated by third party data sources. In some embodiments, a system comprises a computing device and machine readable instructions. The computing device includes a processor and a memory. The machine-readable instructions can be stored in the memory that, when executed by the processor, cause the computing device to receive content from a third party data source based at least in part on a keyword topic. An embedding for the content is generated. The system can classify a portion of the content as associated with the keyword topic. Organizations can be identified from the portions of the content. The system can generate a list from the organizations identified in the content and transmit a notification to a client device regarding the content.

Relevant notifications of third party content

A system may receive a query configured to access a column in a data table. The data table may be in a flat file in a big data storage format. The system may detect the language type of the query and validate the query against the syntax of the language type. The system may also validate an access permission for data in the data table. The access permission may be stored in a permissions database. The system may generate a temporary table including the column with the temporary table configured to support the language type. The system may execute the query against the temporary table to generate a query result based on the temporary table as though it were the underlying data table. The system may enforce column-level or row-level access permissions by excluding columns or rows from the temporary table.

Converting a language type of a query

Systems and methods for identifying data of interest are disclosed. The system may retrieve unstructured data from an internet data source via an alert system or RSS feed. The system may input the unstructured data into various models and scoring systems to determine whether the data is of interest. The models and scoring systems may be executed in order or in parallel. For example, the system may input the unstructured data into a Na&#xef;ve Bayes machine learning model, a long short-term memory (LSTM) machine learning model, a named entity recognition (NER) model, a semantic role labeling (SRL) model, a sentiment scoring algorithm, and/or a gradient boosted regression tree (GBRT) machine learning model. Based on determining that the unstructured data is of interest, a data alert may be generated and transmitted for manual review or as part of an automated decisioning process.

Systems and methods of the present disclosure may read source data corresponding to a source variable and apply a transformation to the source variable to generate an output variable. Accordingly, one such method comprises receiving a request to generate an output variable by applying one or more data transformations to a source variable; before applying an actual data transformation to the source variable, checking a database of prior data transformations that have been applied to source variables to generate existing output variables for a match with the requested one or more data transformations to the source variable; determining that a match exists in the database, wherein the match is associated with an existing output variable; and/or responding to the request by providing the existing output variable associated with the match that exists in the database of prior data transformations.

A system may receive a request for access to a first variable. The request may include a requested action and a variable identifier for the first variable. The request may also have a syntax that is incompatible with first data storage format. The system may parse the request to capture the variable identifier from the request. The system may also look up a location of the first variable in a catalog using the variable identifier. The location of the first variable may include the first data storage format. The system may generate a query to access the first variable. The syntax of the query may be compatible with the first data storage format. The system may then submit the query to access the first data storage format. The query may be configured to complete the requested action.

Querying in big data storage formats

A system may retrieve a pattern from a pattern database with the pattern identifying a type of sensitive data. The system may also retrieve data identified by a variable from a big data management system. The system may then match the data to the pattern to detect the type of sensitive data in the data. An output may be generated in response to the data matching the pattern. A variable access permission may be retrieved for the variable from a permissions repository, a sensitive data permission may be retrieved for the type of sensitive data from the permissions repository, and the variable access permission may be compared to the sensitive data permission to detect a discrepancy.

Systems and methods for tracking sensitive data in a big data environment

A system and method may allow for improved accuracy for address matching. The system may receive an address input and preprocess the address input. The address input may be standardized to create a standardized address input. The standardized address input may be compared to a stored address. The system may calculate a first address matching score based on the comparison. The system may reinvestigate the standardization of the address input and calculate a second address matching score based on a second comparison. The system may compare the first address matching score to the second address matching score to improve accuracy in address matching.

Systems and methods for address matching

A system may read source data corresponding to a source variable and apply a transformation to the source variable to generate an output variable. The transformation may include logic, and the output variable may be configured for ingestion into a big data storage format. The system may record lineage data of the output variable that comprises the transformation and/or the source variable. The system may also receive a request to generate a requested output variable. The requested output variable may be generated from a second transformation that is the same as the first transformation. The system may thus match the first transformation to the second transformation using the lineage data. In response to matching the first transformation to the second transformation, the system may deny the request. The original output variable may be returned in response to the matching the first transformation to the second transformation.

A distributed file system may store a plurality of entity attributes. A node consolidating system may identify similarities between entity attributes for different entities. The node consolidating system may generate an entity graph which displays relationships and similarities between entities in a graphical user interface.

Network node consolidation

A system for data comparison is disclosed. The system may receive a source configuration metadata. The system may configure a data extraction module to extract data from a data set in response to the source configuration metadata. The system may generate a pre-work data from the data set. The system may compare the pre-work data to generate a post-process data set. The system may generate a report corresponding to the post-process data set.

Systems and methods for comparing data across data sources and platforms

Growing community of inventors

Scottsdale, AZ, United States of America

Sandeep Bose