Abstract: Systems, methods, and computer-readable media are disclosed for selecting loan payment terms for improved loan quality and risk management. An exemplary embodiment includes storing first loan data corresponding to a first loan to a first borrower. The first loan may have been funded based on an initial financial disclosure that reflects the financial status of the first borrower during an initial time period when the first loan was funded. First payment terms and second payment terms are stored, and one of the first payment terms or the second payment terms is selected based on whether the first borrower provides the updated financial disclosure. The first loan data is processed consistently with the selected payment terms.

Abstract: In an illustrative embodiment, an automated system determines similarities between properties at a location using customized features sets. The system can generate feature sets for properties from property attribute data received from external and internal sources. The system can transform one or more elements of attribute data of combined internal and external data into customized property attributes that enhance property attribute comparisons. The combined attribute data can be applied to a machine learning algorithm that identifies a portion of the combined attribute data for using in property similarity calculations. Using the identified features, the system can calculate similarity scores identifying an amount of similarity between properties at the location and a property identified in a comparable property query, which can be output to an external device.

Abstract: This disclosure relates to knowledge generation and implementation. A knowledge graph system comprises at least one processor, at least one database communicatively connected to the at least one processor, and a memory storing executable instructions. When executed, the instructions cause the at least one processor to aggregate, from the at least one database, entity data for a plurality of homes. Attribute information identifying geographic locations of the plurality of homes and relationships between pairs of the plurality of homes is extracted from the aggregated data. Knowledge graph data structures are populated with the extracted attribute information. A home knowledge graph is built, having nodes corresponding to the plurality of homes and edges corresponding to the identified relationships. A hierarchical cluster tree structure of the plurality of homes is outputted, wherein levels of the hierarchical cluster tree correspond to clusters of homes determined based in part on the knowledge graph edges.

Abstract: Systems, methods, and computer-readable media are disclosed for testing a software application. An exemplary method includes storing a control file identifying a test case for testing a software application. A first expected result may be extracted from a device storing expected results of the software application, the first expected result being identified by the control file. A first actual result may be extracted from a device storing actual results output by the software application, the first actual result being identified by the control file. The first expected result may be compared with the first actual result to determine whether the first actual result matches the first expected result. A result file indicating whether the test case passed or failed is generated, and the test case has passed when the first actual result matches the first expected result. The result file may be stored in a storage device.

Abstract: In an illustrative embodiment, an automated system determines rental income and location quality for geographic regions using customized data sets. The system can generate customized location feature sets for applying to trained location quality prediction models where the feature sets include hybrid features combining aspects of two or more items of the location feature data into a single hybrid feature and the geographic regions are sized to a predetermined granularity level. Each feature set associated with a geographic region can be applied to a machine learning data model trained to predict rental property income at the respective predefined region from the customized location feature sets. Using the output data from the machine learning data model, the system can calculate location metrics quantifying a rental property income and the location quality for the geographic region.

Abstract: Systems, methods, and computer program products are provided for directing cash flows associated with a mortgage-backed security to back other securities without collapsing the original mortgage-backed security. A mortgage-backed security /an/or a set of loans is analyzed to identify cash flows from mortgages having specific desirable characteristics, and the cash flows are directed to subgroups or pools that support new mortgage-backed securities. The new securities make the desirable cash flows available to an issuer or prospective investor without collapsing the original mortgage-backed security.

Abstract: In an illustrative embodiment, an automated system links data files associated with loan submissions that have different identification attributes. The system may include computing systems and devices for receiving requests from a number of remote computing systems to identify loan products associated with a data file. The system can generate a matching input matrix comparing identification attributes from a first data file to identification attributes of candidate data files. The system can apply attribute matching rules to the matching input matrix to identify other data files that correspond to the same loan product as the first data file despite the data files having different identification attributes. The system can link data files corresponding to the same loan product within a data repository with a product linking key and output the linking key or other data for the loan product to a receiving computing system.

Abstract: In an illustrative embodiment, an automated system assesses risks associated with real estate entities. The system may include computing systems and devices for extracting data attributes for real estate entities from received source data, and the extracted data attributes may each be associated with a particular data level for a real estate entity. The system can link data attributes in adjacent data levels with unique linkage information and compute metrics for each of the real estate entities from the data attributes where each computed metric may be associated with one of the data levels. The system can assess an amount of risk associated with each of the real estate entities based on the computed metrics and present the assessed amount of risk for one or more real estate entities to a remote computing device of a user responsive to receiving a risk assessment request.

Abstract: Systems, methods, and computer-readable storage media are described for processing data change requests. In one exemplary embodiment, a computer-implemented method receives one or more requests in a software production environment for one or more data changes to data from a requestor. The method executes the request(s) in a rollback mode. The method generates a snapshot of the executed request(s). The method also transmits the snapshot to an approver. In response to an approval of the snapshot from the approver, the method also executes the request(s) in a commit mode.

Abstract: Systems, methods, and computer-readable media are disclosed for testing a software application. An exemplary method includes storing a control file identifying a test case for testing a software application. A first expected result may be extracted from a device storing expected results of the software application, the first expected result being identified by the control file. A first actual result may be extracted from a device storing actual results output by the software application, the first actual result being identified by the control file. The first expected result may be compared with the first actual result to determine whether the first actual result matches the first expected result. A result file indicating whether the test case passed or failed is generated, and the test case has passed when the first actual result matches the first expected result. The result file may be stored in a storage device.

Abstract: Systems, methods, and computer-readable media are disclosed for selecting loan payment terms for improved loan quality and risk management. An exemplary embodiment includes storing first loan data corresponding to a first loan to a first borrower. The first loan may have been funded based on an initial financial disclosure that reflects the financial status of the first borrower during an initial time period when the first loan was funded. First payment terms and second payment terms are stored, and one of the first payment terms or the second payment terms is selected based on whether the first borrower provides the updated financial disclosure. The first loan data is processed consistently with the selected payment terms.

Abstract: This disclosure relates to knowledge generation and implementation. A knowledge graph system comprises at least one processor, at least one database communicatively connected to the at least one processor, and a memory storing executable instructions. When executed, the instructions cause the at least one processor to aggregate, from the at least one database, entity data for a plurality of homes. Attribute information identifying geographic locations of the plurality of homes and relationships between pairs of the plurality of homes is extracted from the aggregated data. Knowledge graph data structures are populated with the extracted attribute information. A home knowledge graph is built, having nodes corresponding to the plurality of homes and edges corresponding to the identified relationships. A hierarchical cluster tree structure of the plurality of homes is outputted, wherein levels of the hierarchical cluster tree correspond to clusters of homes determined based in part on the knowledge graph edges.

Abstract: In an illustrative embodiment, an automated system links data files associated with loan submissions that have different identification attributes. The system may include computing systems and devices for receiving requests from a number of remote computing systems to identify loan products associated with a data file. The system can generate a matching input matrix comparing identification attributes from a first data file to identification attributes of candidate data files. The system can apply attribute matching rules to the matching input matrix to identify other data files that correspond to the same loan product as the first data file despite the data files having different identification attributes. The system can link data files corresponding to the same loan product within a data repository with a product linking key and output the linking key or other data for the loan product to a receiving computing system.

Abstract: In an illustrative embodiment, an automated system engineers customized feature vectors from geospatial information system (GIS) metadata. The system may include computing systems and devices for extracting metadata for GIS features located within a predetermined distance of a property from a GIS map file and storing the extracted GIS features within a feature vector. The system can augment each of the extracted GIS features with amplifying data features extracted from external data sources. The system can calculate a distance between the property and each extracted GIS feature, which establishes a relationship between the property and each GIS feature and associated amplifying data features. Amounts of correlation between each of the extracted GIS features and associated amplifying data features within the feature vector and a market assessment of the property location can be identified using a data model trained with a data set customized to characteristics of the property.

Abstract: Systems, methods, and computer-readable media are disclosed for using a synthetic reference structure to determine if an obligation is triggered.

Abstract: Systems, methods, and computer-readable media are disclosed for selecting loan payment terms for improved loan quality and risk management. An exemplary embodiment includes storing first loan data corresponding to a first loan to a first borrower. The first loan may have been funded based on an initial financial disclosure that reflects the financial status of the first borrower during an initial time period when the first loan was funded. First payment terms and second payment terms are stored, and one of the first payment terms or the second payment terms is selected based on whether the first borrower provides the updated financial disclosure. The first loan data is processed consistently with the selected payment terms.

Abstract: Systems and method are provided for testing an infrastructure. The infrastructure may include one or more computers connected by a network. Moreover, each of the computers may include an agent. In one embodiment, the method includes receiving, at a controller, a test request to perform at least one of a plurality of predetermined tests, the predetermined test including one or more parameters associated with performing the predetermined test and one or more expected results from performing the predetermined test. The method further includes determining whether the predetermined test is available at one of the computers. The method also includes sending, by the controller, the predetermined test to one of the computers based on the results of the determining step, such that the agent at the computer performs the predetermined test sent by the controller. Furthermore, the method includes receiving, at the controller, one or more results of the predetermined test performed by the agent at the computer.

Abstract: Embodiments consistent with the present invention provide a credit enhancement structure for risk allocation between parties that minimizes the regulatory capital reserve requirement impact to an institution subject to capital reserve requirement. A subject pool of assets held by the institution, such as a pool of loans, is rated to determine its risk levels. Based on the rated risk levels, a guarantor party agrees to be responsible for a portion of the risk associated with the pool of assets, which may define the maximum risk exposure of the institution holding the asset pool. The risk-rated capital reserve requirements are applied to the asset pool based on the risk level rating and the guarantor's agreed upon risk responsibility such that the institution holds a reduced amount of reserve capital compared to what it would otherwise be required to hold.

Abstract: Systems, methods, and computer-readable storage media are described for processing data change requests. In one exemplary embodiment, a computer-implemented method receives one or more requests in a software production environment for one or more data changes to data from a requestor. The method executes the request(s) in a rollback mode. The method generates a snapshot of the executed request(s). The method also transmits the snapshot to an approver. In response to an approval of the snapshot from the approver, the method also executes the request(s) in a commit mode.

Abstract: Systems, methods, and computer-readable media are disclosed for calculating a housing volatility index. An exemplary embodiment includes accessing stored property value data reflecting first values of real estate properties during a first time period and second values of the real estate properties during a second time period. The second time period may be subsequent to the first time period. The property value data may be processed to identify the first values and the second values, and time intervals between dates of the first values and dates of the second values may be calculated. Value changes of the real estate properties over the time intervals may also be calculated, based on the first values and the second values. A volatility measure for the real estate properties may be determined based on the value changes of the real estate properties over the time intervals, and the volatility measure may be output to a user.