Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains a set of features associated with a customer, wherein the set of features includes profile data from an online professional network. Next, the system uses a statistical model and the features to predict a likelihood of acquiring the customer for an educational technology product. The system then uses the likelihood to generate output for use in targeting the customer with the educational technology product.

Abstract: A system, apparatus, and methods are provided for automatically managing a collection of service instances. A selected or random instance of the service isredline-tested to determine a maximum level of sustained and stable performance (e.g., a maximum or approximate maximum load or throughput of the service instance). This redline value may represent a highest service request rate (e.g., in queries per second or qps) that should be delivered to some or all instances of the service. An expected range of demand for the service is then estimated for a future time period, possibly from analysis and/or observations of past demand, and a maximum and minimum number of instances for handling that range of demand, at an acceptable level of performance, can be determined. During the time period, additional instances may be created and superfluous instances may be removed automatically, based on actual demand.

Abstract: The disclosed embodiments provide a system that performs domain name resolution. During operation, the system uses one or more attributes of a Domain Name System (DNS) query to identify a membership of the DNS query in a grouping of related DNS queries. Next, the system obtains a set of DNS records for resolving the related DNS queries. The system then expedites resolution of subsequent DNS queries in the grouping by transmitting the set of DNS records in a response to the DNS query.

Abstract: The disclosed embodiments provide a system that processes data. During operation, the system obtains a set of features for a customer of an educational technology product. Next, the system uses an account type of the customer to select a statistical model from a set of statistical models for evaluating potential customer spending with the educational technology product. The system then uses the statistical model and the features to predict a potential spending of the customer with the educational technology product. Finally, the system outputs the potential spending for use in managing sales activity with the customer.

Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains a set of features associated with a sales lead for an educational technology product, wherein the set of features includes profile data from an online professional network. Next, the system uses the set of features to generate a set of quality indicators for the sales lead. The system then aggregates the quality indicators into a lead score representing a quality of the sales lead. Finally, the system outputs the lead score for use in managing sales activity with the sales lead.

Abstract: The disclosed embodiments provide a system for performing online hyperparameter tuning in distributed machine learning. During operation, the system uses input data for a first set of versions of a statistical model for a set of entities to calculate a batch of performance metrics for the first set of versions. Next, the system applies an optimization technique to the batch to produce updates to a set of hyperparameters for the statistical model. The system then uses the updates to modulate the execution of a second set of versions of the statistical model for the set of entities. When a new entity is added to the set of entities, the system updates the set of hyperparameters with a new dimension for the new entity.

Abstract: The disclosed embodiments provide a system for performing network routing using a publish-subscribe messaging system. During operation, a node in the system detects a first change in reachability within the network. Next, the node generates a first message comprising the first change for receipt by other nodes in the network through a publish-subscribe messaging system. The node then transmits the first message to the publish-subscribe messaging system. Another node receives the first message, updates a routing database at the other node to reflect the first change, and uses the updated routing database to process network traffic.

Abstract: The disclosed embodiments provide a system that automatically detects a role of a node in a network with a layered topology. During operation, the system uses a local shortest path tree (SPT) for a node in a network with a layered topology to identify one or more additional nodes in the network that are farthest from the node. Next, the system compares the local SPT with a remote SPT for the one or more additional nodes to identify a position of the node in the layered topology. The system then outputs the position of the node for use in configuring the operation of the node in the network.

Abstract: The disclosed embodiments provide a system for performing sub-second network telemetry using a publish-subscribe messaging system. During operation, the system obtains, through the publish-subscribe messaging system, a stream of messages from a set of nodes connected by a set of links in a network. Next, the system analyzes network telemetry data associated with the nodes from the stream of messages. The system then outputs a telemetry result for the network based on the analyzed network telemetry data.

Abstract: The disclosed embodiments provide a system for propagating network configuration policies using a publish-subscribe messaging system. During operation, the system receives, through the publish-subscribe messaging system, one or more messages containing a first representation of a configuration policy from a policy server. Next, the system uses a data model to convert the first representation into a second representation of the configuration policy. The system then uses the second representation to apply the configuration policy during processing of network traffic.

Abstract: The disclosed embodiments provide a system for allocating resources to an application. During operation, the system obtains a set of resource requirements for the application, wherein the resource requirements include a processor allocation and a memory allocation. Next, the system identifies a set of hosts in a set of racks with available resources that meet the resource requirements. The system then selects, for the application, a rack in the set of racks based on a priority associated with resource allocation for the application and a host in the rack based on one or more additional priorities associated with resource allocation for the application. Finally, the system allocates the resources on the host to the application.

Abstract: The disclosed embodiments provide a system for processing data. During operation, the system uses a hierarchical structure of features inputted into a statistical model to obtain a set of groups of the features. Next, the system uses the groups as input to a set of view models for estimating an output of the statistical model. The system then applies the view models to the features to generate a set of view model outputs, wherein each view model output in the set of view model outputs represents an effect of a group in the set of groups on an output of the statistical model. Finally, the system outputs the view model outputs for use in characterizing a performance of the statistical model.

Abstract: The disclosed embodiments provide a system for performing multi-tenancy distribution of a graph database cache. During operation, the system obtains a cache of a set of records in a graph database storing a graph, wherein the graph includes a set of nodes, a set of edges between pairs of nodes in the set of nodes, and a set of predicates. Next, the system identifies one or more records in the cache that fail a validation test. The system then merges a remainder of the cache with online updates to the subset of records to produce a merged version of the cache. Finally, the system distributes the merged version to one or more instances of the graph database for use in processing queries of the graph database.

Abstract: The disclosed embodiments provide a system that improves learner engagement in online discussions. During operation, the system selects an experience level for use in moderating answers to a question submitted to an online forum. Next, the system matches the experience level to a first subset of users in a set of potential respondents to the question. The system then improves an engagement of the first subset of users with the online forum by generating output that targets the first subset of users with the question, prior to displaying the question to a first remainder of the potential respondents that does not include the first subset of users.

Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains a set of predicted growth rates for a first set of customers of a product. Next, the system uses a set of features comprising the predicted growth rates to generate a set of customer segments for the product, wherein each customer segment in the set of customer segments includes a similar growth rate and a similar potential spending. For each customer segment in the set of customer segments, the system uses the similar growth rate and the similar potential spending to calculate a customer lifetime value (CLV) for the customer segment. Finally, the system outputs the CLV with a second set of customers assigned to the customer segment for use in managing sales activity with the second set of customers.

Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains training data containing a first set of customer support tickets and a first set of categories assigned to the first set of customer support tickets by customer support agents. Next, the system uses the training data to produce a statistical model for classifying the customer support tickets into the categories. The system then uses the statistical model to classify a second set of customer support tickets into a second set of categories. Finally, the system generates output for routing the second set of customer support tickets to the customer support agents according to the second set of categories.

Abstract: The disclosed embodiments provide a system that automatically detects a potential microloop condition associated with network convergence. During operation, the system obtains a topology for a network containing a set of nodes connected by a set of links. Next, the system uses the topology to detect a ring containing at least four hops in the network. The system then outputs an indication of a potential microloop condition associated with one or more nodes on the ring to improve improve routing of network traffic by the one or more nodes.

Abstract: The disclosed embodiments provide a system that performs load-based compression of a forwarding table for a node in a network. During operation, the system obtains link utilizations for a set of physical links connected to the node. Next, the system uses the link utilizations to update a set of entries in a forwarding table of the node for use in balancing load across the set of physical links. The system then uses the set of entries to process network traffic at the node.

Abstract: The disclosed embodiments provide a system for processing data. During operation, the system provides a schema for including, by a set of components in a multi-tier architecture, a tracking identifier for an entity instance in the multi-tier architecture. Next, the system identifies, from a set of tracking events received from the multi-tier architecture, a subset of the tracking events containing the tracking identifier. The system then groups the subset of the tracking events into an entity lifecycle for the entity instance. Finally, the system outputs the entity lifecycle for use in assessing a performance of the multi-tier architecture by a consumer of tracking data.

Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains a set of derived data sets for use by a set of clients. For each derived data set in the set of derived data sets, the system produces a default version of the derived data set from multiple versions of the derived data set. The system then outputs the default version and the multiple versions for retrieval by the set of clients through an online data store, an offline data store, and a nearline data store.