Abstract: Data can be received that includes information corresponding to a set of users. Privacy protection protocols that apply to the data can be identified. A subset of the data can be identified as being personally identifiable information (PII) data, where the subset includes a set of PII attributes. The PII attributes can be split into categories based on a format of a data field in the PII attributes. The processed PII data can be combined with non-PII data to create processed client data. It can be determined to add noise to part of the processed PII data. An amount of noise can be determined based on the privacy protection protocols. The amount of noise can be added to part of the processed PII data to produce protected data. A machine-learning model can be trained using the protected data.

Abstract: An organization-based access control (OBAC) system defines resource access rights using graph-based team node trees, each comprising a plurality of hierarchically-connected team nodes. Each team node is associated with a list of members, team resources, and a team-specific access policy that defines the rights of team members to access the team resources. When a node in a tree has one or more descendant nodes, boundary access policies can be generated to define rights, of members of the node, to access resources associated with descendant nodes. Such boundary access policies may grant parent team members different access rights for child team resources than is granted to the child team members. A node management policy can grant rights to manage a portion of a team node tree. Team-specific access policies, boundary access policies, and management policies can include unique references to one or more particular resources, resource attributes, or groups of resources.

Abstract: Techniques are disclosed for generating a database schema using trained machine learning models that, in some embodiments, may include graph neural networks (GNN). A GNN may identify source to target database schema mappings using, among other features of the graph, context data associated with each node in a graph. Context data describes relationships between a particular node and some (or all) of the other nodes in the graph. The system may use this context data (and other graph data) in combination with a trained GNN model to identify a mapping between one or more source database entities to corresponding target database entities.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating a recommended target audience based on determining a predicted attendance utilizing a neural network approach. For example, the disclosed systems can utilize an approximate nearest neighbor algorithm to identify individuals that are within a similarity threshold of invitees for an event. In addition, the disclosed systems can implement an attendance prediction model to determine a probability of an invitee attending the event. The disclosed systems can further determine a predicted attendance for an event based on the individual probabilities. Based on identifying the similar individuals to, and the attendance probabilities for, the invitees, the disclosed systems can generate a recommended target audience to satisfy a target attendance for an event based on a predicted attendance for the event.

Abstract: Techniques are disclosed for generating a database schema using trained machine learning models that, in some embodiments, may include graph neural networks (GNN). A GNN may identify source to target database schema mappings using, among other features of the graph, context data associated with each node in a graph. Context data describes relationships between a particular node and some (or all) of the other nodes in the graph. The system may use this context data (and other graph data) in combination with a trained GNN model to identify a mapping between one or more source database entities to corresponding target database entities.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for providing factors that explain the generated results of a deep neural network (DNN). In embodiments, multiple machine learning models and a DNN are trained on a training dataset. A preliminary set of trained machine learning models with similar results to the trained DNN are selected for further evaluation. The preliminary set of machine learning models may be evaluated using a distribution analysis to select a reduced set of machine learning models. Results produced by the reduced set of machine learning models are compared, point-by-point, to the results produced by the DNN. The best performing machine learning model with generated results that performs closest to the DNN generated results may be selected. One or more factors used by the selected machine learning model are determined.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating a recommended target audience based on determining a predicted attendance utilizing a neural network approach. For example, the disclosed systems can utilize an approximate nearest neighbor algorithm to identify individuals that are within a similarity threshold of invitees for an event. In addition, the disclosed systems can implement an attendance prediction model to determine a probability of an invitee attending the event. The disclosed systems can further determine a predicted attendance for an event based on the individual probabilities. Based on identifying the similar individuals to, and the attendance probabilities for, the invitees, the disclosed systems can generate a recommended target audience to satisfy a target attendance for an event based on a predicted attendance for the event.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for providing factors that explain the generated results of a deep neural network (DNN). In embodiments, multiple machine learning models and a DNN are trained on a training dataset. A preliminary set of trained machine learning models with similar results to the trained DNN are selected for further evaluation. The preliminary set of machine learning models may be evaluated using a distribution analysis to select a reduced set of machine learning models. Results produced by the reduced set of machine learning models are compared, point-by-point, to the results produced by the DNN. The best performing machine learning model with generated results that performs closest to the DNN generated results may be selected. One or more factors used by the selected machine learning model are determined.

Abstract: To facilitate data transfer between two databases, a transfer machine accesses both databases and finds matching records. The transfer machine determines and stores a match status of a record in one database. The match status indicates whether the record corresponds to at least one of the records in the other database, and if so, which record or records in the other database correspond to the record. If the match status indicates that the record matches a record in the other database, the transfer machine determines which record is current and updates the other record. If the match status indicates that a record has no match in the other database, the transfer machine adds a copy of the record to the other database.

Abstract: To facilitate data transfer between two databases, a transfer machine accesses both databases and finds matching records. The transfer machine determines and stores a match status of a record in one database. The match status indicates whether the record corresponds to at least one of the records in the other database, and if so, which record or records in the other database correspond to the record. If the match status indicates that the record matches a record in the other database, the transfer machine determines which record is current and updates the other record. If the match status indicates that a record has no match in the other database, the transfer machine adds a copy of the record to the other database.

Abstract: There is provided a method and system to maintain published contact information. The system includes a storage facility to store contact information of a first entity at the system. The system further includes an interface to electronically publish, via a communications network, the contact information of the first entity to a plurality of users of the system and receive, at the system, information relating to validity of the contact information of the first entity. The information is received via the communications network from a first user of the plurality of users. The system further includes a stored value module automatically to provide a reward to the first user responsive to the receipt of the information relating to the validity of the contact information of the first entity.

Abstract: There is provided a method and system to generate corporate data pertaining to a corporate entity. The system includes an interface to communicate, to each of a plurality of users of a data system, a corporate data attribute relating to a corporate entity and a plurality of candidate data attribute values for the corporate data attribute and to receive, at the system and from the plurality of users, votes for at least one candidate data attribute value of the plurality of candidate data attribute values for the corporate data attribute. The system further includes a vote module automatically to tally the votes and publish vote information based on the votes received from the plurality of users in connection with the plurality of candidate data attribute values for the corporate data attribute.

Abstract: There is provided a method and system to maintain published contact information. The system includes a storage facility to store contact information of a first entity at the system. The system further includes an interface to electronically publish, via a communications network, the contact information of the first entity to a plurality of users of the system and receive, at the system, information relating to validity of the contact information of the first entity. The information is received via the communications network from a first user of the plurality of users. The system further includes a stored value module automatically to provide a reward to the first user responsive to the receipt of the information relating to the validity of the contact information of the first entity.

Abstract: There is provided a method and system to generate corporate data pertaining to a corporate entity. The system includes an interface to communicate, from a data system and via a communications network, a request to a plurality of users of the data system for corporate information relating to a corporate entity and to receive, at the data system and via the communications network, first corporate information relating to the corporate entity from a first user of the plurality of users of the data system responsive to the request. The system further includes a stored value module automatically to provide a reward to the first user responsive to receipt of the first corporate information relating to the corporate entity.

Abstract: There is provided a method and system to incentivize provision of contact information. The system includes an interface to receive first contact information pertaining to a first entity. The first contact information is received from a first user and via a communications network at the interface. The system also includes a stored value module that responds to receipt of the first contact information to award a first predetermined value to the first user. The first predetermined value is redeemable for second contact information pertaining to a second entity. The awarding of the first predetermined value to the first user includes adding the first predetermined value to a total stored value for the first user maintained by the contact information computer system.