Abstract: An online system stores objects representing potential transactions of an enterprise. The online system uses predictor models to determine an aggregate score based on values of the objects associated with a time interval, for example, a month. Each object is configured to take one of a plurality of states. The online system stores historical data describing activities associated with potential transaction objects and uses the stored data for generating the predictor models. The online system categorizes the objects into bins based on states of the objects. The online system may generate different predictions for each category. The online system may use machine learning based models as predictor models. The online system extracts features describing potential transaction objects and provides these as input to the predictor model.

Abstract: The following relates generally to determining an optimal rewards program (e.g., of a credit card or debit card), and purchasing one or more items via the optimal rewards program. In some embodiments, a cardholder initiates a first user-initiated interaction between a bank card and a bank card machine, which generates a first purchase authorization request. One or more processors of a first bank then determine an optimal rewards program for the purchase, and then decline the first purchase authorization request. The cardholder may then initiate a second user-initiated interaction between the bank card and the bank card machine, which generates a second purchase authorization request. One or more processors of a second bank (e.g., a bank of the rewards program) may then authorize the second purchase authorization request. Alternatively, some embodiments complete a purchase according to a determined optimal rewards program with only one user-initiated interaction.

Abstract: An online system stores objects representing potential transactions of an enterprise. The online system uses predictor models to determine an aggregate score based on values of the objects associated with a time interval, for example, a month. Each object is configured to take one of a plurality of states. The online system stores historical data describing activities associated with potential transaction objects and uses the stored data for generating the predictor models. The online system categorizes the objects into bins based on states of the objects. The online system may generate different predictions for each category. The online system may use machine learning based models as predictor models. The online system extracts features describing potential transaction objects and provides these as input to the predictor model.

Abstract: A multi-tenant system stores a hierarchy of machine-learned models, wherein each machine-learned model is configured to receive as input a set of search results and generate as output scores for ranking the set of search results. Each machine-learned model is associated with a set of dimensions. The system evaluates search query performance. Performance below a threshold causes a new model to be generated and added to the hierarchy of models. Upon execution of a new search query associated with the same set of dimensions as the newly created model, the new model is used to rank that search query's search results.

Abstract: A service system provides users with access to online services. As part of providing the services to users, the service system stores data for users in a data storage system. When the service system receives a request from an administrator of the system for user data stored in the data storage system, the service system identifies the data requested by the administrator. The service system also determines policies that apply to the data. The determined policies indicate transformations that are to be performed on the data to protect the privacy of the users. The service system transforms the user data as indicated by the policies and provides the transformed user data to the administrator.

Abstract: A user provides a description of a neural network to a visualization tool. The visualization tool displays a user interface that includes a visual of the neural network based on the description. If the user interacts with a node or connection, for example by placing a cursor on the node/connection in the user interface, the user interface displays information associated with the node/connection. If the user selects a node of a layer, the neural network is applied to an input that corresponds to the selection and the user interface displays the propagation of the input through the neural network. Additionally, the user interface displays results from applying the neural network to the input.

Abstract: A record management system retrieves relevance information through an information retrieval model that models relevance between users, queries, and records based on user interaction data with records. Relevance information between different elements of the record management system are determined through a set of learned transformations in the information retrieval model. The record management system can quickly retrieve relevance information between different elements of the record management system given the set of learned transformations in the information retrieval model, without the need to construct separate systems for different types of relevance information. Moreover, even without access to contents of records, the record management system can determine relevant records for a given query based on user interaction data and the determined relationships between users, queries, and records learned through the information retrieval model.

Abstract: A multi-tenant system stores a hierarchy of machine-learned models, wherein each machine-learned model is configured to receive as input a set of search results and generate as output scores for ranking the set of search results. Each machine-learned model is associated with a set of dimensions. The system evaluates search query performance. Performance below a threshold causes a new model to be generated and added to the hierarchy of models. Upon execution of a new search query associated with the same set of dimensions as the newly created model, the new model is used to rank that search query's search results.

Abstract: A record management system stores records for an organization having a plurality of members and a plurality of groups, and manages accessibility of the records for the organization according to a specified record access policy. The record management system generates an accessibility database that indicates, for each member, records that are explicitly or implicitly accessible by each member such that the records accessible for each member can be quickly determined if needed. A member has explicit access to a record if there is an explicit indication of accessibility between the member and the record. A member has implicit access to a record through membership associations to other members or groups that have access to the record. The record management system also receives search queries from members and returns records that are relevant and accessible to the members based on the accessibility database.

Abstract: A document retrieval system tracks user selections of documents from query search results and uses the selections as proxies for manual user labeling of document relevance. The system trains a model representing the significance of different document features when calculating true document relevance for users. To factor in positional biases inherent in user selections in search results, the system learns positional bias values for different search result positions, such that the positional bias values are accounted for when computing document feature features that are used to compute true document relevance.

Abstract: A multi-tenant system stores a hierarchy of machine-learned models, wherein each machine-learned model is configured to receive as input a set of search results and generate as output scores for ranking the set of search results. Each machine-learned model is associated with a set of dimensions. The system evaluates search query performance. Performance below a threshold causes a new model to be generated and added to the hierarchy of models. Upon execution of a new search query associated with the same set of dimensions as the newly created model, the new model is used to rank that search query's search results.

Abstract: A record management system stores records for an organization having a plurality of members and a plurality of groups, and manages accessibility of the records for the organization according to a specified record access policy. The record management system generates an accessibility database that indicates, for each member, records that are explicitly or implicitly accessible by each member such that the records accessible for each member can be quickly determined if needed. A member has explicit access to a record if there is an explicit indication of accessibility between the member and the record. A member has implicit access to a record through membership associations to other members or groups that have access to the record. The record management system also receives search queries from members and returns records that are relevant and accessible to the members based on the accessibility database.

Abstract: A record management system stores records for an organization having a plurality of members and a plurality of groups, and manages accessibility of the records for the organization according to a specified record access policy. The record management system generates an accessibility database that indicates, for each member, records that are explicitly or implicitly accessible by each member such that the records accessible for each member can be quickly determined if needed. A member has explicit access to a record if there is an explicit indication of accessibility between the member and the record. A member has implicit access to a record through membership associations to other members or groups that have access to the record. The record management system also receives search queries from members and returns records that are relevant and accessible to the members based on the accessibility database.

Abstract: A service system provides users with access to online services. As part of providing the services to users, the service system stores data for users in a data storage system. When the service system receives a request from an administrator of the system for user data stored in the data storage system, the service system identifies the data requested by the administrator. The service system also determines policies that apply to the data. The determined policies indicate transformations that are to be performed on the data to protect the privacy of the users. The service system transforms the user data as indicated by the policies and provides the transformed user data to the administrator.

Abstract: A multi-tenant system stores a hierarchy of machine-learned models, wherein each machine-learned model is configured to receive as input a set of search results and generate as output scores for ranking the set of search results. Each machine-learned model is associated with a set of dimensions. The system evaluates search query performance. Performance below a threshold causes a new model to be generated and added to the hierarchy of models. Upon execution of a new search query associated with the same set of dimensions as the newly created model, the new model is used to rank that search query's search results.

Abstract: A document retrieval system tracks user selections of documents from query search results and uses the selections as proxies for manual user labeling of document relevance. The system trains a model representing the significance of different document features when calculating true document relevance for users. To factor in positional biases inherent in user selections in search results, the system learns positional bias values for different search result positions, such that the positional bias values are accounted for when computing document feature features that are used to compute true document relevance.

Abstract: An online system stores objects representing potential transactions of an enterprise. The online system uses predictor models to determine an aggregate score based on values of the objects associated with a time interval, for example, a month. Each object is configured to take one of a plurality of states. The online system stores historical data describing activities associated with potential transaction objects and uses the stored data for generating the predictor models. The online system categorizes the objects into bins based on states of the objects. The online system may generate different predictions for each category. The online system may use machine learning based models as predictor models. The online system extracts features describing potential transaction objects and provides these as input to the predictor model.

Abstract: An online system stores objects representing potential transactions of an enterprise. The online system uses predictor models to determine an aggregate score based on values of the objects associated with a time interval, for example, a month. Each object is configured to take one of a plurality of states. The online system stores historical data describing activities associated with potential transaction objects and uses the stored data for generating the predictor models. The online system categorizes the objects into bins based on states of the objects. The online system may generate different predictions for each category. The online system may use machine learning based models as predictor models. The online system extracts features describing potential transaction objects and provides these as input to the predictor model.

Abstract: An online system stores objects representing potential transactions of an enterprise. The online system uses machine learning techniques to predict likelihood of success for a potential transaction object. The online system stores historical data describing activities associated with potential transaction objects and uses the stored data as training dataset for a predictor model. The online system extracts features describing potential transaction objects and provides these as input to the predictor model for predicting the likelihood of success of a given potential transaction. The online system may use predictions of likelihood of success of potential transactions to identify a set of potential transactions that should be acted upon to maximize the benefit the enterprise within a time interval, for example, by the end of the current month.

Abstract: A system stores objects of different types and allows search over the objects. The system receives search requests and processes them to determine search results matching the search criteria. The system ranks the search results based on weighted aggregates of features describing objects represented by each search result. The system monitors search results that were accessed by user for further information and marks them as accessed results. The system adjusts the feature weights used for ranking search results to optimize the ranking of the search results. The system analyzes the result of using the adjusted feature weights on past searches that are stored in the system. The system determines an aggregate accessed results rank for each adjusted set of weights. The system selects a set of feature weights that optimizes the aggregate accessed results rank for past searches.