Abstract: Techniques for securely storing and processing data for training data generation are provided. In one technique, multiple encrypted records are retrieved from a first persistent storage. For each encrypted record, that record is decrypted in memory to generate a decrypted record that comprises multiple attribute values. Then, based on the attribute values and a definition of multiple features of a machine-learned model, multiple feature values are generated and stored, along with a label, in a training instance, which is then stored in a second persistent storage. One or more machine learning techniques are used to train the machine-learned model based on training data that includes the training instances that are stored in the second persistent storage.

Abstract: An online system receives a request to confirm a transaction that is associated with an order. The system accepts or declines the transaction based on whether an amount associated with the pending transaction is likely to exceed an expected amount of the order by more than a threshold value. To determine the threshold, the system trains a first model to predict an overspend for an order and then trains a second model to predict an amount of error associated with the predictions from the first model. The outputs of the first model and the second model provide a mean and a variance for an expected distribution of the overspend. If the actual overspend amount for the transaction exists in too high of a percentile of the distribution, the transaction may be flagged for review or declined.

Abstract: Techniques for a flexible data security and machine learning system for merging third-party data are provided. In one technique, the system receives a data set from a third-party entity and receives selection data that indicates that the third-party entity selected a set of data security policies that includes an encryption option and a data mixing option from among multiple data mixing options. In response to receiving the selection data, the system stores data that associates the set of data security policies with the data set, encrypts the data set according to the encryption option, and persistently stores the encrypted data set. Later, the system decrypts the encrypted data set in volatile memory, generates, based on the data mixing option, training data based on the decrypted version of the data set, trains a machine-learned model based on the training data, and stores the machine-learned model in association with the data set.

Abstract: Techniques for a flexible data security and machine learning system for merging third-party data are provided. In one technique, the system receives a data set from a third-party entity and receives selection data that indicates that the third-party entity selected a set of data security policies that includes an encryption option and a data mixing option from among multiple data mixing options. In response to receiving the selection data, the system stores data that associates the set of data security policies with the data set, encrypts the data set according to the encryption option, and persistently stores the encrypted data set. Later, the system decrypts the encrypted data set in volatile memory, generates, based on the data mixing option, training data based on the decrypted version of the data set, trains a machine-learned model based on the training data, and stores the machine-learned model in association with the data set.

Abstract: Techniques for securely storing and processing data for training data generation are provided. In one technique, multiple encrypted records are retrieved from a first persistent storage. For each encrypted record, that record is decrypted in memory to generate a decrypted record that comprises multiple attribute values. Then, based on the attribute values and a definition of multiple features of a machine-learned model, multiple feature values are generated and stored, along with a label, in a training instance, which is then stored in a second persistent storage. One or more machine learning techniques are used to train the machine-learned model based on training data that includes the training instances that are stored in the second persistent storage.

Abstract: Entity resolution techniques for matching entity records from different data sources are provided. In one technique, an entity record from a source database is identified along with multiple data items included therein. Each data item corresponds to an attribute of multiple source attributes. For one of the data items that corresponds to a first source attribute, multiple target attributes are identified. A first query is generated that includes the data items and associates the data item with each of the multiple target attributes. A second query that is different than the first query is also generated. Two searches are performed of a target database: one based on the first query and the other based on the second query. A scoring model generates multiple scores, one for each search result. It is determined whether the entity record matches an entity record in the target database based on the set of scores.

Abstract: Entity resolution techniques for matching entity records from different data sources are provided. In one technique, an entity record from a source database is identified along with multiple data items included therein. Each data item corresponds to an attribute of multiple source attributes. For one of the data items that corresponds to a first source attribute, multiple target attributes are identified. A first query is generated that includes the data items and associates the data item with each of the multiple target attributes. A second query that is different than the first query is also generated. Two searches are performed of a target database: one based on the first query and the other based on the second query. A scoring model generates multiple scores, one for each search result. It is determined whether the entity record matches an entity record in the target database based on the set of scores.

Abstract: Techniques for managing multiple computing systems are provided. A system comprises a content delivery system (CDS) and an entity identification system (EIS). The CDS causes a content item that is associated with a content delivery campaign to be delivered over a computer network to a computing device of a user. The CDS detects that the user performed an action relative to the content item and, in response, creates an action record that indicates a particular entity associated with the user and that indicates an account that is associated with the content item and causes the action record to be made available to the EIS. The EIS, based on the account indicated in the action record, identifies a particular account from among multiple accounts indicated in an account database and searches the particular account for an entity (if any) that matches the particular entity.

Abstract: Techniques for managing multiple computing systems are provided. A system comprises a content delivery system (CDS) and an entity identification system (EIS). The CDS causes a content item that is associated with a content delivery campaign to be delivered over a computer network to a computing device of a user. The CDS detects that the user performed an action relative to the content item and, in response, creates an action record that indicates a particular entity associated with the user and that indicates an account that is associated with the content item and causes the action record to be made available to the EIS. The EIS, based on the account indicated in the action record, identifies a particular account from among multiple accounts indicated in an account database and searches the particular account for an entity (if any) that matches the particular entity.

Abstract: Techniques for integrating an entity identification system and a content delivery system are provided. The entity identification system identifies multiple entities that have been identified, by multiple users, through the entity identification system. The entity identification system determines a stage for each identified entity, creates multiple entity groups (one for each different stage), and makes the entity groups available to the content delivery system. The content delivery system assigns each entity group to a different content delivery campaign. In response to receiving a content request from a client device, the content delivery system determines an identifier associated with the client device, where the identifier is in a particular entity group. Based on the identifier, a content delivery campaign that corresponds to the particular entity group is determined and a content item associated with the content delivery campaign is identified and transmitted over a network to the client device.

Abstract: Methods, systems, and computer program products for a distributed processing system and database for managing, performing, measuring, evaluating, codifying, and teaching social selling are described. Metric data corresponding to a user of a social network system is obtained and one or more components of a social selling index score are computed. The social selling index score is computed based on the one or more components. A graphical interface, using at least one hardware processor, is generated based on the one or more components and the social selling index score, the graphical interface having a first portion that includes a chart representing a first element associated with the social selling index score and a second portion that includes text representing a second element associated with the social selling index score.

Abstract: The present disclosure presents a method and an apparatus for transmitting symbol files. For example, the method may include storing one or more symbol files at a local server, identifying a symbol file associated with a crash dump file by parsing the crash dump file, and determining whether the identified symbol file is to be transmitted to a central symbol server. Furthermore, such an example method may include retrieving the identified symbol file from the local server based at least on the determining, and transmitting the retrieved symbol file to the central symbol file server based at least on the determining. As such, transmission of symbol files is achieved.