Abstract: In one implementation, a computing device to provide a graphical user interface (GUI) for presenting content includes one or more processors; a network interface to establish a network connection with a remote server system; a display to output a plurality of graphical elements as part of the GUI; one or more input devices to receive user input related to the plurality of graphical elements; and memory storing instructions that, when executed, cause the one or more processors to perform operations including selecting a first content element; selecting second content elements; detecting a third content element comprising a content summary of the second content elements; and outputting, in the GUI on the display, a first graphical element for the first content element and a third graphical element for the third content element, wherein second graphical elements for the second content elements are hidden or collapsed in the GUI.

Abstract: Methods and systems for optimizing item assortments are disclosed. One method includes receiving a request for an optimized assortment. Data relating to items within a selected initial item assortment and item universe is accessed. Constraints are applied to the items in the assortment to arrive at an optimized item assortment. Constraints include goals for optimization, lock in and lock out rules, and item attribute rules. The method may be performed by a system including one or more computing devices communicating via a network with one or more data storage devices.

Abstract: An inland freight management module for managing inland moves of freight from a plurality of vendor supply locations to port includes a profile maintenance component, a load planning component, and a load routing and booking component. The profile maintenance component is adapted for maintaining an inland planning zone profile including information relating to a plurality of inland planning zones generated according to one or more customs districts. The load planning component is programmed for planning field consolidation of one or more container loads via a multi-stop route between the plurality of vendor supply locations, where the multi-stop route is generated within one of the plurality of inland planning zones.

Abstract: Methods and systems for generating link predictions are provided. In one aspect, a method includes initializing a graph including a plurality of nodes representing selections of items in a training dataset to a multivariate normal distribution having a predetermined mean and a predetermined initial variance, the items in the training dataset comprising items in an item collection. The method includes, for each node in the graph, modeling embeddings for the node as embeddings of each neighboring node having a shared edge, with each being updated based at least in part on a transition probability and a variance. A predetermined number of iterations of updating are executed each iteration including an updated variance based on a learning rate. Based on receipt of an identification of an item from among the item collection, a plurality of predicted selections of items are identified using the embeddings for a node corresponding to the item.

Abstract: Multitask learning is applied to predict a customer's propensity to purchase an item within a particular category of items. Then, the network is tuned using transfer learning for a specific promotional campaign. Retail revenue and promotional revenue are jointly optimized, conditioned on customer trust. Accordingly, a particular promotional program may be selected that is specific to the user.

Abstract: Methods and systems for facilitating delivery of goods from a retail location to a customer are disclosed. In one method, a request is received from a customer user which includes an order for goods to be delivered from a retail store. One or more delivery users within a predefined geographic area shared with a location of the customer user are identified. A delivery user agrees to pick up the customer's order and deliver the requested goods to the customer's home. Confirmation messages are automatically sent and received when the delivery user picks up the customer's order and again when the order is delivered to the customer. The delivery user can earn rewards or payments upon completion of successful delivery.

Abstract: A node management protocol is disclosed herein. The protocol can be used for task distribution in multi-node systems. The node management protocol can implement a cooperation-based task distribution algorithm that does not rely on consensus. When a task is ingested into a cluster of nodes, the nodes can compete to handle the task. A transport layer helps coordinate among nodes and facilitates the handling of work. A session expiry protocol handles node failures with the remaining nodes reassigning work.

Abstract: Warehouse automation and methods of automatically sorting and sequencing items can be implemented to streamline and expedite order fulfillment and store replenishment processes in a cost-effective manner. Some embodiments described herein include sorting items to a truck-level and inducting those items for a first truck into a buffering and sequencing system. Items can temporarily accumulate in the buffering and sequencing system and thereafter be discharged in a desired sequence as the items become available within the buffering and sequencing system. In some embodiments, the buffering and sequencing system is used to sequence items for loading one or more store aisle-ready carts in a sequence that corresponds to a store aisle layout.

Abstract: A method for reducing peak electrical demand of a building includes generating a baseline electrical demand profile over a target time period from a model. The baseline electrical demand profile can be used to define a policy including a peak management period having at least a first sub-period and a subsequent second sub-period, the first sub-period having a first temperature set point for at least one air handling system of the building that is different from a normal operating temperature set point, the second sub-period having a second temperature set point different from both the normal operating temperature set point and the first temperature set point, and implementing the policy. The model can be generated from one or more of historical electrical data for the building, weather forecast data, building and equipment operating schedules, sales data, and data based on information received from a video camera located in the building.

Abstract: A plurality of network sensors are configured to sense the operations of a data network and, responsive to sensing the operations of the data network, generate event data objects that record the operations of the data network. One or more decorator pipelines are configured to decorate the event data objects with data other than from operations of the data network. A security frontend is configured to generate a graphical user interface (GUI) configured to provide, to a user, query-authoring tools, receiving a query in a structured language, provide responsive to receiving the query, results to the query from historic event data that was decorated before the query was received, receive approval for the query, and later execute the query on new event data that has been decorated after the approval for the query is received.

Abstract: Methods and systems for generating item recommendations are disclosed. One method includes sampling from a weighted node-based graph to generate a sampled graph, wherein sampling includes selecting a plurality of nodes and, for each selected node, one or more node pairs. The selection of the node pairs is based at least in part based on a weight assigned to the node pair in the weighted node-based graph. The method further includes aggregating information from the one or more neighboring nodes into each corresponding node of the plurality of nodes in the sampled graph to generate a vector representation of the sampled graph. The method also includes applying a loss function to the vector representation of the sampled graph to generate a modified vector representation. The modified vector representation is used to generate, in response to identification of an item from an item collection, a selection of one or more recommended items from within the item collection.

Abstract: Methods and systems are described for optimizing delivery modes used to transport items to a customer. A delivery optimization system includes an online ordering system, a delivery mode optimizer, an order allocator, a cartonization engine, and a ship label and manifest generator. The delivery mode optimizer selects an optimal shipping mode based on information received from carriers. The lowest cost option to deliver the goods to the destination by a promised delivery date is selected at the time the order is received. A shipping node is selected that can supply the items needed to fulfill the order within the desired timeframe. Cartons are selected to package the items in the order in the most cost effective manner. The delivery mode is reevaluated after the order is prepared for shipment to determine if available shipping options have changed.

Abstract: Methods and systems for forecasting demand for a plurality of items are provided. In particular, the demand forecasting system and methods described herein are useful for predicting demand of products in a retail context. Forecast models are built and used to score incoming sales data to predict future demand for items. Forecast models are validated by evaluating actual demand against predicted demand and using that information to inform how future ensemble forecast will be generated. Forecasts may be broken down into smaller components to satisfy a variety of requests for data from client applications.

Abstract: A method includes receiving a first post from an electronic source including first content; determining a source identifier; determining an attribute for the source by broadcasting the first post to a first plurality of filter graph definitions configured to identify attributes of sources according to the respective filter graph definition; and storing in memory, as a source profile identified by the source identifier for the source, the attribute for the source; receiving a second post from the source including second content; determining a source identifier; using the source identifier, querying the memory to access the source profile; correlating the second post with attributes of the source stored in the source profile to produce a correlated second post; and broadcasting the correlated second post to a second plurality of filter graph definitions configured to identify posts with high value information according to the respective filter graph definition.