Abstract: Examples are disclosed for detecting synthetic online entities that may be used for fraudulent purposes or other purposes. In some aspects, a computing system can generate a data structure that includes nodes and links between the nodes. The nodes can represent online entities and the links can represent geographic associations or transactional associations between pairs of online entities. These associations can be identified from electronic transactions involving the online entities. The computing system can determine, from the links between the nodes, that a degree of connectivity among a subset of the nodes exceeds a threshold connectivity. The degree of connectivity indicates electronic communications involving online entities represented by the subset of the nodes. The computing system can transmit, based on the degree of connectivity exceeding the threshold connectivity, an alert indicating a potential synthetic entity (e.g., potentially fraudulent activity) within the subset of the nodes.

Abstract: A telecommunications network server system provides a digital identifier to a user device. The digital identifier may include identification data corresponding to a user of the user device. In addition, the telecommunications network server system receives, from one or more third-party systems, requests to authenticate the user for an electronic transaction with the respective third-party system. The telecommunications network server system provides a unique electronic transaction code to each third-party system. Responsive to receiving from the user device one of the unique electronic transaction codes, the telecommunications network server system provides, to the respective third-party system, authentication of the user.

Abstract: Various aspects involve a monotonic recurrent neural network (MRNN) trained for risk assessment or other purposes. For instance, the MRNN is trained to compute a risk indicator from a predictor variable. Training the MRNN includes adjusting weights of nodes of the MRNN subject to a set of monotonicity constraints, wherein the set of monotonicity constraints causes output risk indicators computed by the RNN to be a monotonic function of input predictor variables. The trained monotonic RNN can be used to generate an output risk indicator for a target entity.

Abstract: In some aspects, a computing system can determine a set of attributes based on analyzing input data using attribute templates written in a production-ready programming language. The computing system can generate attribute definitions for the set of attributes using the attribute templates and deploy the attribute definitions for the set of attributes to a production environment of a software program. The software program is written in a programming language compatible with the production-ready programming language. The computing system can monitor the performance of the set of attributes in the production environment of the software program and cause the attribute definitions of the plurality of attributes to be modified based on the monitoring.

Abstract: Certain aspects involve providing automated performance monitoring of statistical models. For example, a processing device is used for performing a statistical analysis on information in an archive to extract historical data, scores, and attributes. The processing device calculates performance metrics based at least in part on the historical data, scores, and attributes. The processing device pre-calculates summary performance data based at least in part on the performance metrics. The summary performance data is stored in files with predefined layouts, which are stored in a non-transitory, computer-readable medium. Segmented data is presented from a file to a user through a graphical user interface (GUI). In some aspects, various reports of the segmented data are presented interactively by detecting a selection by the user of a segmentation and displaying the corresponding segmented data.

Abstract: Systems and methods for automated path-based recommendation for risk mitigation are provided. An entity assessment server, responsive to a request for a recommendation for modifying a current risk assessment score of an entity to a target nsk assessment score, accesses an input attribute vector for the entity and clusters of entities defined by historical attribute vectors. The entity assessment server assigns the input attribute vector to a particular cluster and determines a requirement on movement from a first point to a second point in a multi-dimensional space based on the statistics computed from the particular cluster. The first point corresponds to the current risk assessment score and the second point corresponds to the target risk assessment score. The entity assessment server computes an attribute-change vector so that a path defined by the attribute-change vector complies with the requirement and generates the recommendation from the attribute-change vector.

Abstract: A durability assessment system may receive a request, from a computing system, for a durability index describing an entity. The durability assessment system may determine the durability index based on information about the resource usage by the entity, such as a resource availability score or a resource allocation score. The durability assessment system may compare the obtained resource availability score and resource allocation score to ranges associated with a set of durability indices. Based on the comparison, the durability assessment system may determine a durability index for the entity. The durability index may indicate an ability of the entity to return accessed resources. In some cases, the durability assessment system may provide the durability index to an allocation computing system that is configured to determine whether to grant access to resources based on the durability index.

Abstract: Various aspects involve a lagged prediction model trained for risk assessment or other purposes. For instance, a risk assessment computing system receives a risk assessment query for a target entity and provides an input predictor record for the target entity to a lagged prediction model. The input predictor record includes a first group of lagged values from a first time-series attribute associated with the target entity. The lagged prediction model is trained by implementing a group feature selection technique configured to select the first time-series attribute as input and to deselect a second time-series attribute associated with the target entity. The risk assessment computing system computes an output risk indicator from the input predictor record and transmits the output risk indicator to a remote computing system. The output risk indicator can be used to control access by the target entity to one or more interactive computing environments.

Abstract: Certain aspects involve a machine-learning query system that uses a dual deep learning network to service queries and other requests. In one example, a machine-learning query system services a query received from a client computing system. A dual deep learning network included in the machine-learning query system matches an unstructured input data object, received from the client computing system, to an unstructured reference data object. The matching may include generating an input feature vector by an embedding subnetwork, based on the unstructured input data object. The matching may also include generating an output probability by a relationship subnetwork, based on the input feature vector and a relationship feature vector that is based on the unstructured reference data object. The machine-learning query system may transmit a responsive message to the client system.

Abstract: In some aspects, systems and methods for efficiently clustering a large-scale dataset for improving the construction and training of machine-learning models, such as neural network models, are provided. A dataset used for training a neural network model configured can be clustered into a first set of clusters and a second set of clusters. The neural network model can be constructed with a number of nodes in a hidden layer that is based on the number of clusters in the first set of clusters. The neural network can be trained based on training samples selected from the second set of clusters. In some aspects, the trained neural network model can be utilized to satisfy risk assessment queries to compute output risk indicators for target entities. The output risk indicator can be used to control access to one or more interactive computing environments by the target entities.

Abstract: In some aspects, a computing system can control access of a user computing device to a resource. The computing system can obtain an access request submitted by a user computing device. The computing system can verify permission information in the access request to determine that the access request is valid. If the access request is valid, the computing system submits an authentication request to request an authentication system to authenticate the user and obtains authentication results generated by the authentication system. The computing system further provides, based on the authentication results, an access control decision for the access request.

Abstract: In some aspects, a computing system can generate and optimize a neural network for risk assessment. The neural network can be trained to enforce a monotonic relationship between each of the input predictor variables and an output risk indicator. The training of the neural network can involve solving an optimization problem under a monotonic constraint. This constrained optimization problem can be converted to an unconstrained problem by introducing a Lagrangian expression and by introducing a term approximating the monotonic constraint. Additional regularization terms can also be introduced into the optimization problem. The optimized neural network can be used both for accurately determining risk indicators for target entities using predictor variables and determining explanation codes for the predictor variables. Further, the risk indicators can be utilized to control the access by a target entity to an interactive computing environment for accessing services provided by one or more institutions.

Abstract: Various aspects of this disclosure provide digital data processing systems for using encrypted variant data objects to facilitate queries of sensitive data. In one example, a digital data processing system can receive sensitive data about an entity. The digital data processing system can create, in an identity data repository and from the sensitive data, a searchable secure entity data object for the entity. The searchable secure entity data object is usable for servicing a query regarding the entity. For instance, a transformed query parameter can be generated from a query parameter in the query. The query can be serviced by matching the transformed query parameter to tokenized variant data in the searchable secure entity data object and retrieving tokenized sensitive data from the searchable secure entity data object.

Abstract: An online identity can be verified based on data from multiple identity sources stored in a blockchain. For example, a request for a token is received from an entity for authenticating an online identity of the entity to an online service. The request can be stored in a blockchain that represents the online identity of the entity by adding a new block to the blockchain. The new block can include data indicating the request for the token. The token can be generated based on the one or more ordered blocks in the blockchain. The token can be transmitted to the entity. The token can be received from the online service. Confirmation of the online identity of the entity can be transmitted to the online service based on receiving the token from the online service.

Abstract: In some aspects, an entity-resolution computing system for entity resolution is provided. The entity-resolution computing system includes an entity-resolution server configured for correlating data objects from an identity data repository that contains account or transaction data for entities based on the data objects including a common portion of the account or transaction data. The entity-resolution server updates the identity data repository to include an entity identifier that links the data objects and indicates that the data objects refer to a common entity. The entity-resolution server creates an entity-resolution data structure having the data objects with the entity identifier and a new variant data object containing a modified version of account or transaction data that match the common entity.

Abstract: An exchange processing system may include multiple exchange components that are respectively included in multiple computing systems. A central exchange component may receive a request to enable access to secured data, the request having identity data encrypted via an identity encryption module and inquiry data encrypted via a first request encryption module. The central exchange component may decrypt the identity data via the identity encryption module, and decrypt the inquiry data via the first request encryption module. Response data may be generated from secured data that is selected based on the identity and inquiry data. The central exchange component may encrypt the response data via a second request encryption module and re-encrypt the identity data via the identity encryption module. The encrypted identity and response data may be provided to a second remote exchange module.

Abstract: Aspects and examples are disclosed for improving multi-factor authentication techniques to control access to secured electronic resources. In one example, a decisioning computer system evaluates, based on a passive-dimension decision process, an access request, received from a user device, for a secured electronic resource. The passive-dimension decision process can evaluate dimensions associated with the access request, such as identity or device characteristics, to determine whether the dimensions of the access request are outside of norms for the user. Based on the passive-dimension decision model, the decisioning computing device may communicate to the user device an access decision, the access decision describing one or more of an access authorization, a denial of access, or a supplemental authentication challenge.

Abstract: In some aspects, a content-extraction system can receive a query from a client device and generate a result set of digital content responsive to the query. For instance, the content-extraction system can obtain, from a search system, a set of digital content matching one or more keywords. The content-extraction system can exclude digital content items lacking core content, digital content items with duplicative content, or both. In some aspects, the content-extraction system can determine, for one or more remaining digital content items, a content attribute score. The content-extraction system can select, as the result set of digital content, a subset of digital content based on the content attribute scores. The content-extraction system can output the result set to the client device.

Abstract: Certain aspects involve optimizing neural networks or other models for assessing risks and generating explanatory data regarding predictor variables used in the model. In one example, a system identifies predictor variables. The system generates a neural network for determining a relationship between each predictor variable and a risk indicator. The system performs a factor analysis on the predictor variables to determine common factors. The system iteratively adjusts the neural network so that (i) a monotonic relationship exists between each common factor and the risk indicator and (ii) a respective variance inflation factor for each common factor is sufficiently low. Each variance inflation factor indicates multicollinearity among the common factors. The adjusted neural network can be used to generate explanatory indicating relationships between (i) changes in the risk indicator and (ii) changes in at least some common factors.

Abstract: Certain aspects involve updating data structures to indicate relationships between attribute trends and response variables used for training automated modeling systems. For example, a data structure stores data for training an automated modeling algorithm. The training data includes attribute values for multiple entities over a time period. A computing system generates, for each entity, at least one trend attribute that is a function of a respective time series of attribute values. The computing system modifies the data structure to include the generated trend attributes and updates the training data to include trend attribute values for the trend attributes. The computing system trains the automated modeling algorithm with the trend attribute values from the data structure. In some aspects, trend attributes are generated by applying a frequency transform to a time series of attribute values and selecting, as trend attributes, some of the coefficients generated by the frequency transform.