Abstract: Systems and methods for creating a two-dimensional orthographic map that models an environment using images captured with a camera and an augmented reality (AR) engine. The interior has at least one object with one or more planes that are parallel to each other. A method can include annotating the at least one image with a plurality of horizontal lines or vertical lines, each horizontal line or vertical line corresponding to an edge of the at least one object in at least one of the one or more planes, determining, an orientation of a projection plane that is parallel to each of the one or more planes, estimating an offset for each of the one or more planes relative to the projection plane, and rendering, based on the offset for each of the one or more planes, a two-dimensional orthographic map that models the interior environment.

Abstract: A computer system and method for performing property inspections. Digital media is received in a computer vision image analysis system from one or more user devices via a network and a determination is made regarding an environment type associated with the received digital media. One or more objects are determined that are located in the determined environment and which are present in the received digital media. A determination is made regarding an absence of objects in the received digital media contingent upon the determined environment type based upon a set of rules.

Abstract: Systems and methods are provided for detecting when a user uses one or both hands to interact with a device having a physical or virtual keyboard. In one implementation, one-handed typing is determined by analyzing intragroup and intergroup keyflight timing distributions between different groups of clustered keys, each cluster having distinctly different proximal properties. A statistical measure made between the intragroup and intergroup keyflight timing distributions may be performed to determine one-handed or two-handed typing input, which may be used to enhance a user experience by adapting a viewing or input element to an appropriate hand setting. In another implementation, the detection may be used as input to determine a likelihood of suspected coaching fraud for online banking applications. In yet another implementation, the detection of one-handed typing is used as an input to bot detection algorithms to reduce false positives from other modalities.

Abstract: Certain embodiments of the disclosed technology include systems and methods for increasing efficiency in the detection of identity-based fraud indicators associated with a loan application. A method is provided that includes receiving applicant data associated with a loan application having a plurality of applicants. The application data includes at least a name, a social security number, and a street address for each of the plurality of applicants. The method includes querying one or more databases with the applicant data; receiving a plurality of independent information in response to the querying; determining a validity indication of the applicant data; creating disambiguated applicant records; determining relationships among the disambiguated applicant records; scoring at least one parameter of the applicant data; determining one or more indicators of fraud based on the scoring; and outputting, for display, one or more indicators of fraud.

Abstract: Embodiments of the disclosed technology include systems and methods for identifying one or more entities associated with activities. In an example implementation, a method includes determining one or more geographical regions proximate to the plurality of locations associated with the one or more activities; determining connections between one or more identities of a population and a plurality of related entities associated with the one or more identities; determining geographical information associated with related entities; weighting one or more metrics for each of the identities based on the geographical information associated with the related entities and the or more geographical regions proximate to the plurality of locations associated with the one or more activities; scoring the one or more weighted metrics; and providing, based on the scoring, an indication of a likelihood that the one or more identities of the population are associated with the one or more activities.

Abstract: Systems and methods are disclosed herein for detecting entity migration. A method is provided for receiving container information for all known addresses in the United States. The container information can include address records, person or business entities associated with the address records, and temporal information associating the entities with the address records. The method includes determining, with one or more special-purpose computer processors in communication with a memory, migration data based on the container information. The method includes extracting metrics from the migration data. The metrics can include velocity of migration data; simultaneous movement of individuals within a predetermined time period; distance moved; and/or age of the person or business entities. The method can include determining, based at least in part on outliers associated with the metrics, one or more indicators of fraud; and outputting, for display, the one or more indicators of the fraud.

Abstract: Certain implementations of the disclosed technology may include systems, methods, and apparatus for inferring the performance of rejected credit applicants using non-tradeline data. According to an example implementation, a method is provided for evaluating factors that may indicate financial distress and/or future credit performance associated with an applicant. In an example implementation, the method may include receiving applicant information associated with an applicant of a credit application. Responsive to a query, the method may include receiving by at least one processor, non-tradeline data related to the applicant. The method includes scoring, using a predictive scoring model, and based at least in part on the non-tradeline data, a prediction of the applicant's future credit performance. The method includes generating, based on the scoring, an estimated credit performance of the applicant over a predetermined period; and outputting an indication of the estimated credit performance.

Abstract: Certain embodiments of the disclosed technology include systems and methods for increasing efficiency in the detection of identity-based fraud indicators. A method is provided that includes: receiving entity-supplied information comprising at least a name, a social security number (SSN), and a street address associated with a request for a payment or a benefit; querying one or more databases with the entity-supplied information; receiving a plurality of information in response to the querying; determining a validity indication of the entity supplied information; creating disambiguated entity records; determining relationships among the disambiguated records; scoring, based at least in part on determining the relationships among the disambiguated entity records, at least one parameter of the entity-supplied information; determining one or more indicators of fraud based on the scoring; and outputting, for display, one or more indicators of fraud.

Abstract: Certain embodiments of the disclosed technology include systems and methods for increasing efficiency in the detection of identity-based fraud indicators. A method is provided that includes: receiving entity-supplied information comprising at least a name, a social security number (SSN), and a street address associated with a request for a payment or a benefit; querying one or more databases with the entity-supplied information; receiving a plurality of information in response to the querying; determining a validity indication of the entity supplied information; creating disambiguated entity records; determining relationships among the disambiguated records; scoring, based at least in part on determining the relationships among the disambiguated entity records, at least one parameter of the entity-supplied information; determining one or more indicators of fraud based on the scoring; and outputting, for display, one or more indicators of fraud.

Abstract: Certain embodiments of the disclosed technology include systems and methods for increasing efficiency in the detection of identity-based fraud indicators associated with a loan application. A method is provided that includes receiving applicant data associated with a loan application having a plurality of applicants. The application data includes at least a name, a social security number, and a street address for each of the plurality of applicants. The method includes querying one or more databases with the applicant data; receiving a plurality of independent information in response to the querying; determining a validity indication of the applicant data; creating disambiguated applicant records; determining relationships among the disambiguated applicant records; scoring at least one parameter of the applicant data; determining one or more indicators of fraud based on the scoring; and outputting, for display, one or more indicators of fraud.

Abstract: Certain implementations of the disclosed technology include systems and methods for external linking based on hierarchal level weightings. The method may include associating external query data having one or more query field values with a record in a linked hierarchical database. The linked hierarchical database may include a plurality of records, each record having a record identifier and representing an entity in a hierarchy, each record associated with a hierarchy level, each record including one or more fields, each field configured to contain a field value. The associating may include receiving the external query data, wherein the external query data includes one or more search values; and identifying, from the plurality of records in the linked hierarchical database, one or more matched fields having field values that at least partially match the one or more search values.

Abstract: Certain implementations of the disclosed technology include systems and methods for internal co-convergence using clustering when there is hierarchy in the data structure. A method is included for clustering hierarchical database records into a first set of clusters having corresponding first cluster identifications (IDs), each hierarchical database record including one or more field values, the clustering based at least in part on determining similarity among corresponding field values of the hierarchical database records. The method includes receiving parent-child hierarchical relationship information for the hierarchical database records, re-clustering at least a portion of the hierarchical database records into a second set of clusters having corresponding second cluster IDs, the re-clustering based at least in part on the received parent-child hierarchical relationship information, and outputting hierarchical database record information, based at least in part on the re-clustering.

Abstract: Disclosed is a system for, and method of, recycling field value weights as computed for database linking purposes. Such field value weights may be used for a search operation. In some embodiments, such weights may be used for a search operation prior to their values stabilizing during an iterative linking operation.

Abstract: Embodiment of the disclosed technology include systems and methods for identifying one or more entities associated with activities. In an example implementation, a method includes determining one or more geographical regions proximate to the plurality of locations associated with the one or more activities; determining connections between one or more identities of a population and a plurality of related entities associated with the one or more identities; determining geographical information associated with related entities; weighting one or more metrics for each of the identities based on the geographical information associated with the related entities and the or more geographical regions proximate to the plurality of locations associated with the one or more activities; scoring the one or more weighted metrics; and providing, based on the scoring, an indication of a likelihood that the one or more identities of the population are associated with the one or more activities.

Abstract: Certain implementations of the disclosed technology include systems and methods for external linking based on hierarchal level weightings. The method may include associating external query data having one or more query field values with a record in a linked hierarchical database. The linked hierarchical database may include a plurality of records, each record having a record identifier and representing an entity in a hierarchy, each record associated with a hierarchy level, each record including one or more fields, each field configured to contain a field value. The associating may include receiving the external query data, wherein the external query data includes one or more search values; and identifying, from the plurality of records in the linked hierarchical database, one or more matched fields having field values that at least partially match the one or more search values.

Abstract: Certain implementations of the disclosed technology include systems and methods for internal co-convergence using clustering when there is hierarchy in the data structure. A method is included for clustering hierarchical database records into a first set of clusters having corresponding first cluster identifications (IDs), each hierarchical database record including one or more field values, the clustering based at least in part on determining similarity among corresponding field values of the hierarchical database records. The method includes receiving parent-child hierarchical relationship information for the hierarchical database records, re-clustering at least a portion of the hierarchical database records into a second set of clusters having corresponding second cluster IDs, the re-clustering based at least in part on the received parent-child hierarchical relationship information, and outputting hierarchical database record information, based at least in part on the re-clustering.

Abstract: Certain implementations of the disclosed technology may include systems, methods, and apparatus for inferring the performance of rejected credit applicants using non-tradeline data. According to an example implementation, a method is provided for evaluating factors that may indicate financial distress and/or future credit performance associated with an applicant. In an example implementation, the method may include receiving applicant information associated with an applicant of a credit application. Responsive to a query, the method may include receiving by at least one processor, non-tradeline data related to the applicant. The method includes scoring, using a predictive scoring model, and based at least in part on the non-tradeline data, a prediction of the applicant's future credit performance. The method includes generating, based on the scoring, an estimated credit performance of the applicant over a predetermined period; and outputting an indication of the estimated credit performance.

Abstract: Certain implementations of the disclosed technology include systems and methods for linking entities in an internal database by utilizing co-convergence and clustering. The method may include clustering database records into a first set of clusters having corresponding first cluster identifications (IDs). The clustering may be based at least in part on determining similarity among corresponding field values. The method may include associating mutually matching database records, by performing at least one matching iteration for each of the database records. The method may include determining similarity among corresponding field values of the database records, re-clustering at least a portion of the database records into a second set of clusters, the re-clustering based at least in part on the associating mutually matching database records and on the determining similarity among corresponding field values of the database records.

Abstract: Certain implementations of the disclosed technology include systems and methods for internal co-convergence using clustering when there is hierarchy in the data structure. A method is included for clustering hierarchical database records into a first set of clusters having corresponding first cluster identifications (IDs), each hierarchical database record including one or more field values, the clustering based at least in part on determining similarity among corresponding field values of the hierarchical database records. The method includes receiving parent-child hierarchical relationship information for the hierarchical database records, re-clustering at least a portion of the hierarchical database records into a second set of clusters having corresponding second cluster IDs, the re-clustering based at least in part on the received parent-child hierarchical relationship information, and outputting hierarchical database record information, based at least in part on the re-clustering.

Abstract: Certain implementations of the disclosed technology include systems and methods for external linking based on hierarchal level weightings. The method may include associating external query data having one or more query field values with a record in a linked hierarchical database. The linked hierarchical database may include a plurality of records, each record having a record identifier and representing an entity in a hierarchy, each record associated with a hierarchy level, each record including one or more fields, each field configured to contain a field value. The associating may include receiving the external query data, wherein the external query data includes one or more search values; and identifying, from the plurality of records in the linked hierarchical database, one or more matched fields having field values that at least partially match the one or more search values.