Abstract: Aspects of the present disclosure are directed to extracting textual information from image documents. In one embodiment, a system, upon receiving a request to extract textual information from an image document, a digital processing system performs character recognition based on content of the image document using multiple approaches to generate corresponding texts. The texts are then combined to determine a result text representing the textual information contained in the image document. The result is then provided as a response to the request.

Abstract: Disclosed herein is a declarative modeling paradigm for a graph model, graph-physicalization, delta load/offload, automatic generation of sub-graphs based on user entitlements, a graph-pipeline for low-code graph file formats, and machine-learning pipeline for analysis of the graph model. In a particular aspect, a computer-implemented process includes generating a graphical user interface comprising one or more tools configured to allow a user to build and visualize a graph model based on data, obtaining the data from one or more sources, receiving input from the user via the graphical user interface, where the input comprises a request to create at least two nodes representing logical entities within the data and at least one edge representing one or more relationships between the logical entities, generating the graph model based on the input from the user, analyzing the data using the graph model, and output results based on the analyzing.

Abstract: Machine learning techniques are disclosed for predicting a task event such as a service completion event based on a predefined workflow. In one aspect a method includes obtaining initial data for a service request (e.g., an account application), enriching the initial data with data from one or more repositories of an enterprise executing the service request, generating a data structure comprising independent variables extracted from the enriched data, receiving a request for a prediction of a completion time for the service request (e.g., an account opening event) at a first time during processing of the service request in accordance with each workflow, in response to receiving the request for the prediction, inputting the data structure into a machine-learning regression model, predicting, using the machine-learning regression model, a completion time for the service request, and providing the completion time for the service request.

Abstract: Method includes generating a base model by training a pretrained model using a base training dataset including first training datapoints identifying tables in historical document images that include the tables and text, where the generated base model is configured to extract the tables as objects; and generating a table extraction model by training the base model using an enhanced training dataset including second training datapoints that are different from the first training datapoints and identify a plurality of cells disposed in each of the tables in a row direction and a column direction. The table extraction model is trained to output content of the tables and table information in an XML format, the table information including cell level information of the plurality of cells that is searchable via a query configured to provide target content that corresponds to one or more cells.

Abstract: Machine learning techniques are disclosed for rebuilding transactions to predict cash position. In one aspect a method includes obtaining data for an original transaction, classifying the original transaction into a class of multiple classes based on the data, predicting first tranche delay days for the original transaction based on the class and the data, predicting a tranche count for the original transaction based on the class and the data, predicting a tranche interval for the original transaction based on the class and the data; and rebuilding the original transaction as one or more future transactions based on the class, the first tranche delay days, the tranche count, and tranche interval. Each of the one or more future transactions comprise an updated amount of the original transaction, an updated date upon which the original transaction is anticipated, or both.

Abstract: Techniques are disclosed as an optimization data system for eliminating correlated independent variables programmatically from data with ranked exclusion scores. The system can obtain an initial dataset comprising variables, determine a set of correlation values by analyzing linear correlation between the variables, generate a correlation matrix using at least in part the set of correlation values and corresponding variables from the initial data, calculate exclusion scores for the variables in the correlation matrix that exhibit multicollinearity, and update the initial dataset by removing at least one variable with the highest exclusion score from the variables to generate an updated dataset comprising optimized variables. The steps for correlation and elimination of variables are iterated until an updated dataset without any correlation is obtained and then a machine learning model may be trained using the updated dataset.

Abstract: A machine-learning recommendation system implemented based on game theory for providing recommendations to a first party based on their requirements while also ensuring the recommendation makes sense to a second party. The system can obtain historical data and train a machine-learning model using the historical data. The training includes playing a game between a first player and a second player. The game is played using a minmax theorem that is evaluated with a loss function comprising a first component that represents error in a prediction of a user and product combination and a second component that represents error in a prediction of a value of a product. The game is played until an equilibrium point has been reached at which a final value corresponding to a product to be recommended is determined and the machine-learning model is adapted to minimize the difference between the final value and ground truth information.

Abstract: Systems, methods, and other embodiments associated with a technique for using micro frontends to build a runtime version of a base application are described. In one embodiment, the method allows for selected micro frontends to be incorporated into the base application. Metadata corresponding to the selected micro frontend is identified and parsed to identify at least one or more application programming interfaces (APIs) that are defined in the metadata. The identified APIs are incorporated with the micro frontends to create a final version of the micro frontend. The runtime version of the base application is constructed by combining the final version of the micro frontends with the base application.

Abstract: Techniques are disclosed for creating a workspace. A data processing system receives a request to create a workspace to implement a portion of a model deployed in a production environment. One or more data objects and associated metadata thereof relevant to the portion of the model, and an execution venue for the workspace are obtained. A set of instructions is generated for executing the one or more data objects and the associated metadata in the workspace. The workspace is created within the execution venue by instantiating the portion of the model, the one or more data objects, and the associated metadata in the workspace. The portion of the model in the workspace is processed using the one or more data objects and the associated metadata in accordance with the set of instructions, and the production environment is updated by the data processing system based on the processing.

Abstract: A bill verification system for verifying bill records associated with an entity account is disclosed. The system receives a request to verify a bill record associated with an entity account. The system identifies a bill level model to be used for verifying the bill record and detects based on the bill level model, bill level anomaly information for the bill record. The system additionally identifies a bill line level model to be used for verifying one or more bill lines in the bill record and detects based on the bill line level model, bill line level anomaly information for the bill record. The system then aggregates the bill level anomaly information and the bill line level anomaly information to generate a bill verification report for the bill record. The system provides the bill verification report as a response to the request received to verify the bill record.

Abstract: Systems, methods, and other embodiments for ML-Based automated below-the-line threshold tuning include, in one embodiment, training an ML model to predict probabilities that an event is fraudulent on a set of events (i) sampled from a set of historic events labeled by an alerting engine as either above-the-line events or below-the-line events on either side of a threshold line indicating that an event is suspicious, and (ii) confirmed to be either fraudulent or not fraudulent; determining that the alerting engine should be tuned based on differences between probability values predicted for the events by the trained machine learning model and the labels applied to the events; generating a tuned threshold value for the threshold line based at least in part on the probability values predicted by the machine learning model; and tuning the alerting engine by replacing a threshold value with the tuned threshold value to adjust the threshold line.

Abstract: Systems, methods, and other embodiments associated with controlling an execution pipeline are described. In one embodiment, a method includes generating an execution pipeline for executing a plurality of tasks. The example method may also include evaluating execution definitions of the tasks to identify execution properties of the plurality of tasks. The example method may also include assigning each task to an execution environment selected from a set of execution environments based upon execution properties of the task matching execution properties of the execution environments. The example method may also include controlling the execution pipeline to execute each task within the assigned execution environments.

Abstract: Systems, methods, and other embodiments associated with a framework for compliance report generation are described. In one embodiment, a method includes receiving a data source definition of a set of data sources comprising data for populating compliance reports. The example method may also include retrieving a compliance report definition for a compliance report for a reporting entity. The example method may also include constructing and rendering a user interface populated with a set of user interface elements generated based upon the set of data sources and the compliance report definition. The example method may also include generating the compliance report according to the compliance report definition. The compliance report is populated with data from the set of data sources. The compliance report is sent over a computing network to a remote computing device of the reporting entity.

Abstract: Techniques for handling bulk file processing. One technique includes receiving a request to process transactions within a bulk file, consolidating the transactions into batches based on parameters used to define the transactions, processing a first set of exception validations for each of the batches, storing information for each of the batches that satisfies the first set of exception validations within a set of tables, processing, using JMS Queues and the set of tables, a second set of exception validations for each of the transactions within the batches that satisfy the first set of exception validations, collating, using a timer job and the set of tables, each of the transactions into subsequent batches based on whether each of the transactions satisfies or does not satisfies the second set of exception validations, and accounting each of the transactions in the subsequent batches that satisfy the second set of exception validations.

Abstract: Techniques for automatically deploying a version of a compute, both rule based and model based, with its dependencies when approved for deployment using one or more governance processes. One technique includes generating a compute fitting defined requirements and capable of executing on a defined model objective, generating a deployable archive bundle of the compute with dependencies based on a record of a lineage of the logical building blocks in dependency, analyzing performance of the compute with respect to a production compute deployed within a production environment, determining the performance of the compute is superior to the performance of the production compute based on the analyzing, and replacing the production compute in the production environment with the compute using the deployable archive bundle to facilitate deployment.

Abstract: Techniques are disclosed for attribution analysis in analytical workflows. A data processing system (DPS) obtains an overall model comprising one or more sub-models. The DPS selects an output variable of the overall model for which attribution of changes is to be performed, and a plurality of input variables against which changes are to be attributed to. The overall model is initially executed with respect to a data set of values for the plurality of input variables to generate a base result for the output variable. The overall model is iteratively executed based on a condition associated with the plurality of input variables to obtain a new result for the output variable. In each iteration, a value of an input variable is changed with respect to the data set of values and a change in the output variable with respect to the base result is attributed to the corresponding input variable.

Abstract: Systems, methods, and other embodiments associated with managing transactions communicated over a blockchain network are described. In one embodiment, a method includes receiving a transaction to communicate over the blockchain network, and validating the transaction using hardcoded properties. The example method may also include populating values into the parent transaction table and the child transaction table, and using such tables to facilitate the communication of the transaction over the blockchain network.

Abstract: Techniques are disclosed for creating a workspace. A data processing system receives a request to create a workspace to implement a portion of a model deployed in a production environment. One or more data objects and associated metadata thereof relevant to the portion of the model, and an execution venue for the workspace are obtained. A set of instructions is generated for executing the one or more data objects and the associated metadata in the workspace. The workspace is created within the execution venue by instantiating the portion of the model, the one or more data objects, and the associated metadata in the workspace. The portion of the model in the workspace is processed using the one or more data objects and the associated metadata in accordance with the set of instructions, and the production environment is updated by the data processing system based on the processing.

Abstract: Techniques are disclosed for attribution analysis in analytical workflows. A data processing system (DPS) obtains an overall model comprising one or more sub-models. The DPS selects an output variable of the overall model for which attribution of changes is to be performed, and a plurality of input variables against which changes are to be attributed to. The overall model is initially executed with respect to a data set of values for the plurality of input variables to generate a base result for the output variable. The overall model is iteratively executed based on a condition associated with the plurality of input variables to obtain a new result for the output variable. In each iteration, a value of an input variable is changed with respect to the data set of values and a change in the output variable with respect to the base result is attributed to the corresponding input variable.

Abstract: Techniques for retaining in-memory dataframes beyond an in-memory processing session. One technique includes receiving a request to execute a first run having a first set of tasks, creating a first session to execute the first run, and executing the first run in the first session using a dataframe constructed for a dataset defined as a component of the first run. The executing the first run generates an updated dataframe. The technique further includes receiving a request to execute a second run having a second set of tasks. A dependency exists between the first run and the second run based on a condition that the dataset is defined as a component of the first run and the second run. The technique further includes creating a second session to execute the second run, and executing the second run in the second session using the updated dataframe for the dataset.