Abstract: An interactive visualization tool for displaying metrics associated with inventory related output from a replenishment simulation for an enterprise supply chain is described. Predicted values for metrics associated with simulation output may be received on a per item, per node, per epoch basis for a plurality of items associated with the supply chain at a plurality of nodes of the supply chain over a plurality of epochs. A visualization tool user interface may be rendered that includes item and node menus enabling user selection of varying granularity levels for viewing the metrics. The metrics may be aggregated according to a presently selected level of granularity, and represented within a single graphical view of the user interface to visualize projected inventory positions of items across nodes of the supply chain. The aggregated metrics may include an expected projection and a worst-case projection for one or more types of the metrics.

Abstract: Systems and methods for model evaluation. A protected class model that satisfies an accuracy threshold is built by using: data sets for use by a modeling system being evaluated, and protected class membership information for each data set. A target for the protected class model is a protected class membership variable indicating membership in a protected class. Each predictor of the protected class model is a predictor of an evaluated model used by the modeling system. A target of the evaluated model is different from the target of the protected class model. Each predictor is a set of one or more variables of the data sets. For each predictor of the protected class model, a protected class model impact ranking value and a modeling system impact ranking value are determined.

Abstract: Fluid supply, monitoring and control system from LPG supply vehicles to tank trucks, the vehicle has a LPG liquid level gauger, an output line over which it is located in a fluid way a solenoid valve which allows or cuts the LPG flow besides of a flowmeter which measures the amount that flows through the said output line, a fluid coupled hose to the said output line with a connector which allows to safely couple to a stationary tank; the system also includes the use of a mobile computer device, a central that has at least one desktop computer device connected to a WIFI data network of mobile phone data network with which it communicates with the mobile device.

Abstract: Embodiments are disclosed for a method for machine-learning model accuracy. The method includes generating prediction training data based on training predictions and corresponding probabilities of the training predictions. A classifier of a machine-learning model generates the training predictions. The method also includes training a prediction accuracy model to determine whether the training predictions generated by the machine-learning model are correct. Additionally, the method includes generating predictions in response to corresponding client transactions for the machine-learning model. Further, the method includes determining whether the predictions are accurate using the prediction accuracy model. Also, the method includes providing client predictions corresponding to the client transactions based on the determination.

Abstract: A system and method are disclosed for solving subsequent runs of a supply chain planning problem modeled as a multi-objective hierarchical linear programming problem. Embodiments further include receiving supply chain input data for a supply chain planning problem, modeling the supply chain planning problem as a multi-objective hierarchal linear programming problem having a first objective and at least one additional objective, solving a base run of the multi-objective hierarchical linear programming problem for the first objective and the at least one additional objective, generating a base plan by converting a solution of the base run of the multi-objective hierarchical linear programming problem, receiving one or more changes to the supply chain input data, identifying primal feasibility change of the one or more changes that affect only primal feasibility, and identifying dual feasibility changes of the one or more changes that affect only dual feasibility.

Abstract: In various embodiments, a stylization application generates designs that reflect stylistic preferences. In operation, the stylization application computes characterization information based on a first design and a trained machine-learning model that maps one or more designs to characterization information associated with one or more styles. The stylization application then computes a style score based on the characterization information and a target style that is included in the one or more styles. Subsequently, the stylization application generates a second design based on the style score, where the second design is more representative of the target style than the first design. Advantageously, because the stylization application can substantially increase the number of designs that can be generated based on the target style in a given amount of time, relative to more manual prior art techniques, the overall quality of the design ultimately selected for production can be improved.

Abstract: A server computer system receives a dataset of candidate hybrid seeds for planting on one or more target fields, which comprises data regarding one or more hybrid seeds, probability of success values associated with each of the one or more hybrid seeds that describe a probability of a successful yield, and historical agricultural data associated with each of the one or more hybrid seeds further receives one or more properties for one or more target fields, and selects a subset of the one or more hybrid seeds based on the probabilities of success values.

Abstract: According to one or more embodiments of the disclosure, a service deploys a first service connector to a first deployment network of a first organization and a second service connector to a second deployment network of a second organization. The service receives a selected visibility offering by the first organization and a selected visibility intent for the second organization. The service determines a data sharing policy by matching the selected visibility offering by the first organization to the selected visibility intent for the second organization. The service configures the first service connector to capture data specified by the data sharing policy from the first deployment network and provide that data to the second service connector.

Abstract: An autonomous or semi-autonomous vehicle fleet comprising a plurality of autonomous or semi-autonomous vehicles for providing an assortment of items to a customer or a potential customer after such customer or potential customer summons the one or more autonomous or semi-autonomous vehicles in an unstructured open or closed environment. Each autonomous or semi-autonomous vehicle comprises one or more compartments configured to contain and secure the assortment of the items to be selected once the summoned autonomous or semi-autonomous vehicle arrives to a customer or potential customer.

Abstract: An online concierge system allows users to order items within discrete time intervals later than a time when an order was received. Each order may require a different set of characteristics for fulfilment by shoppers. Because different shoppers may have different capabilities, it is most efficient to reserve shoppers with specialized characteristics for orders that require them. The online concierge system maintains a set of hierarchical structures for different characteristics of shoppers, with each level in a hierarchical structure having a value. To select a shopper to fulfill an order, the online concierge system scores identifies groups of shoppers having characteristics capable of fulfilling the order based on levels in the hierarchical structure for each characteristic of a group. A shopper from a group having a minimum score is selected to fulfill the order.

Abstract: Quick service restaurants with car wash systems and traffic management systems for managing customer traffic and routing customers who have made food-only purchases and customers who have purchased both a food item and a carwash service. In some examples, graphical user interfaces incorporated in point of sale systems display time predictions for the delivery of food items and carwash services to aid and encourage customer selection of both food items and carwash services.

Abstract: A system to provide an automated risk relationship resource allocation tool via back-end application computer server of an enterprise. A resource allocation data store may contain electronic records representing requested resource allocations between the enterprise and a plurality of entities. The server may receive an indication of a selected requested resource allocation and retrieve, from the resource allocation data store, the electronic record associated with the selected requested resource allocation. The server may execute a machine learning algorithm to generate an overall score for the selected requested resource allocation and generate a request health index via an analytic model for the entity associated with the selected requested resource allocation. The system may then support a graphical interactive user interface display via a distributed communication network, the interactive user interface display providing resource allocation data including the overall score and the request health index.

Abstract: An online concierge system allows users to order items from a warehouse having multiple physical locations, allowing a user to order items at any given warehouse location. To select a warehouse location for a warehouse selected by a user, the online concierge system identifies a set of items that the user has a threshold likelihood of purchasing from prior orders by the user. For each of a set of warehouse locations, the online concierge system applies a machine-learned item availability model to each item of the identified set. From the availabilities of items of the set at each warehouse location of the set, the online concierge system selects a warehouse location. The online concierge system identifies an inventory of items from the selected warehouse location to the user for inclusion in an order.

Abstract: Systems and methods for pre-processing data to facilitate efficient and accurate machine learning are provided. The data may include market data. The pre-processing may include partitioning the data into windows assigning categories to windows generate a series of vectors. The series of vectors then being input into a computer system that executes a machine learning algorithm to efficiently train a neural network used to identify structure or patterns therein.

Abstract: Embodiments optimize inventory allocation of a retail item, where the retail item is allocated from a plurality of different fulfillment centers to a plurality of different customer groups. Embodiments receive historical sales data for the retail item and estimate demand model parameters. Embodiments generate a network including first nodes corresponding to the fulfillment centers, second nodes corresponding to the customer groups, and third nodes between the first nodes and the second nodes, each of the third nodes corresponding to one of the second nodes. Embodiments generate an initial feasible inventory allocation from the first nodes to the second nodes and solves a minimum cost flow problem for the network to generate an optimal inventory allocation.

Abstract: Examples provide a system and method for managing non-notifying customer orders for pickup. An order manager component identifies orders received from customers that typically do not provide advance notification prior to arrival at an order pickup location. A prioritization component assigns a priority to each order based on a per-customer confidence level. Customers providing notification and new customers receive the highest priority. Non-notifying customers having consistent pickup times associated with a threshold minimum number of previous orders receive a second highest priority. Non-notifying customers having inconsistent pickup arrival times and/or fewer than the threshold number of previous orders receive lower priority. A routing schedule is generated for pre-staging the orders based on the assigned priorities, pre-staging area capacity, and/or bot capacity. Totes are moved to the prestaging area based on instructions provided in the routing schedule.

Abstract: A system and method to optimize dynamic review generation. A user device associated with a user is selected to provide a review of a merchant. A weighted event factor associated at least a portion of a plurality of websites to which the review can be redirected is identified. Based on the weighted event factor, a first website of the plurality of websites to which to redirect the user device is determined. A dynamic redirection container is transmitted that redirects the client device to the first website, wherein the dynamic redirection container receives a posted review of the merchant at the first website. Based on the posted review associated with the merchant, the weighted event factor is updated.

Abstract: The present disclosure generally provides techniques for analyzing and displaying the order execution quality of market instruments traded during a relevant period, or lifetime, of the order. The utilization of quote information in calculating a normalization factor allows for comparisons across instruments, orders, and days for instruments with a publicly available price irrespective of executed volume. A calculated Z score illustrates the quality of an order execution for a specific traded time as compared to all possible random executions. Moreover, the techniques disclosed herein allow for the comparison of execution quality across market instruments, orders sizes, and other variables via a graphical user interface and other data visualization tools, and can encapsulate evaluation methods using other adjusted Z score thresholds and/or alternatively take into account desirable volume weighting when calculating the standard deviation.

Abstract: A method of managing a plurality of washrooms in a facility for servicing by service personnel and, more particularly, for establishing servicing operations which provide for service of at least selected of the dispensers before their consumable product supply falls below a pre-selected refill value.

Abstract: A method for visualizing flow direction in a distribution network includes receiving, on a hardware device, Geographic Information System (GIS) data corresponding to the distribution network from a GIS database. The distribution network includes equipment to facilitate distribution of a commodity over a distribution area, and the GIS data includes information relating to distribution of the commodity. Commodity vectorized measurement data indicative of at least a flow direction of the commodity over the distribution area is generated based, at least in part, on a comparison of a current measurement value of the commodity to a reference measurement value of the commodity. The commodity vectorized measurement data is dynamically displayed on a geographic map display including imagery representative of the distribution network contained in the GIS data.