Abstract: In an embodiment, a method includes receiving training data representing historic consumer demand for products, detecting changepoints in that data that may be associated with disruptive events, identifying relevant data for modeling, performing clustering, processing configuration information, training one or more machine learning models that are capable of evaluating other received data more accurately, and outputting results to a user display device.

Abstract: Input data comprises an order to provide a quantity of one or more finished goods to a site. Software is programmed for: accessing information that defines an architecture of a supply chain network comprising a plurality of sites connected by a plurality of path fragments; generating one or more path solutions to fulfill the order; removing one or more loops from the one or more path solutions; generating based on the one or more path solutions and the one or more removed loops, one or more revised path solutions; outputting the one or more revised path solutions for display on a client device; and transmitting, only to computers of the sites of a revised subset of a plurality of path fragments, a plurality of signals to initiate movement of one or more of raw materials or finished goods.

Abstract: In one embodiment, a method can access an expense line for a travel expense for an enterprise. The expense line is the subject of a procurement action under a relevant contract. The method can use a first machine learning model, determining a category associated with the expense line. The method can evaluate the expense line using the category associated with the expense line and a table of categories that are procurable with references to related travel contracts. The method can determine a match between a description field of the expense line and description fields of historic invoice records associated with travel contracts. In response to determining the match, the method can execute a responsive action for the expense line, wherein the responsive action includes generating a notification to a user, marking the expense line, and initiating a workflow to apply the contract to the expense line.

Abstract: Embodiments of the disclosed technologies provide solutions for automatically reading digital electronic documents that contain tables and correctly extracting table data, rows and columns from the documents with high accuracy and high throughput. Embodiments are capable of converting a table portion of a read-only document to a searchable, editable data record using text rectangle (TR)-level numerical data that indicates probabilities of TRs belonging to canonicals and at least one convolutional neural network (CNN) that processes the TR-level numerical data to produce table-level numerical data.

Abstract: In one embodiment, a method includes detecting activity of one or more agents that modifies a processing state of a first of multiple invoices, each invoice requesting approval. The activity is conducted by the one or more agents through interacting with the procurement processing system. The method includes updating, based on the detected activity, an invoice interaction history record associated with the first invoice in an invoice interaction history datastore communicatively coupled to the procurement processing system. The method includes generating one or more metrics regarding activity of the agents affecting a processing state of the invoices based on the updated invoice interaction history datastore. The method includes providing the one or more metrics for presentation to the procurement processing system.

Abstract: Embodiments provides a method executed by a server computer executing a supply chain network analysis application of a supply chain model. The method includes receiving supply chain network data associated with a supply chain network having one or more supply chain nodes. The method then programmatically executes inferences on the supply chain network data using one or more machine learning models and one or more heuristic algorithms to implement descriptive analytics, diagnostic analytics, and prescriptive analytics to create and store one or more scenario prescriptions that specify one or more changes to the one or more supply chain nodes. The method performs steps for programmatically executing inferences on the supply chain network data that includes extracting one or more data features at a path level, the one or more data features indicating descriptive insights related to one or more paths in the supply chain network.

Abstract: In an embodiment, a computer-implemented method comprises storing, in one or more data repositories, transactional data relating to past transactions involving a plurality of commodities between a plurality of buyer entities and a plurality of supplier entities; calculating metric data of one or more overages from the transactional data, wherein each of the one or more overages indicates an amount to which a cost of a commodity item as specified in an invoice exceeds a cost of the commodity item as specified in a requisition or a purchase order, the invoice being generated in response to the requisition or the purchase order; receiving, from a computer associated with a buyer entity, a request to generate a requisition or a purchase order for one or more commodity items; identifying, from the request, a supplier identification (ID) associated with a particular supplier entity of the plurality of supplier entities or a commodity ID associated with a particular commodity of the plurality of commodities, for a p

Abstract: In an embodiment, a system disclosed herein receives input information relating to an unmanned aerial vehicle, ground delivery assets, and user preferences or configurations for delivery routes. The system processes the inputted information and determines an optimized delivery route that utilizes the unmanned aerial vehicle and the ground delivery assets.

Abstract: The computer-implemented method utilizes machine learning models to classify input data records. The method includes selecting machine learning models from a plurality of machine learning models using a router model and generating classification inferences for each selected model. The classification inferences include factors indicating the probability of the input data record belonging to various candidate classes. Any one of the plurality of machine learning models is configured to use a weight matrix calculated as the sum of a base weight matrix and a model-associated difference matrix obtained as a product of two low-rank matrices. The classification inferences from selected models are then combined to create an overall classification inference, providing factors related to the probability of the input data belonging to each candidate class. This method enables effective classification by leveraging multiple machine learning models.

Abstract: A computer implemented method comprising receiving invoice data comprising at least one of invoice descriptions and invoice characters from user computers, each of the invoice descriptions and invoice characters defines contexts and patterns, wherein each of the invoice data comprising a supplier-customer information that corresponds to a supplier-customer transaction; analyzing the at least one of the invoice descriptions and the invoice characters with corresponding contexts and patterns; determining that amount of the invoice characters is more than a threshold number of characters, for performing: matching invoice data, invoice characters with predefined historical invoice data that corresponds to the same supplier-customer information; computing a similarity score for each of the invoice data; and displaying recommendations including first account codes to map the one or more first account codes to each of the one or more invoice data based on the similarity score; determining that amount of the invoice

Abstract: A computer-implemented method for validating supplier data is provided. The method includes accessing a spend management interface of a spend management system. The spend management interface may receive supplier data from a supplier computer via user interface widgets of the spend management interface. A country identifier is received from the supplier computer via a country widget and a currency identifier is received via a currency widget of the user interface widgets. One or more parameters associated with the country identifier and currency identifier are identified within a validation database of the spend management system and customized user interface widgets are generated based on the one or more parameters. The spend management interface is electronically updated to present the customized user interface widgets to the supplier computer. Supplier data is received from the supplier computer via the customized user interface widgets and the supplier data is programmatically validated.

Abstract: The present disclosure provides for a method of automatically updating a digitally stored model of an electronic contract over the lifetime of a contract, including a step of receiving an update to an attribute of a digitally stored contract model. Further, retrieving, from a digital data store, model description data and a plurality of answer values. Based on the model description data and answer values, creating a graph of answer data and variables required in the electronic contract as nodes and edges, where nodes represent the answer data and variables, and edges represent dependencies of the nodes. Next, removing edges that are determined from first variables to second variables that the first variables had been declared as using. From the update to the attributes of the contract model, removing one or more nodes corresponding to the one or more variables that are not directly referenceable by the document.

Abstract: Commodity category values can be determined automatically for suppliers in an e-procurement system using a computer-implemented process that is supplier-focused and uses successive heuristics, supplemented with machine learning models that predict category and subcategory values based on supplier names and invoice descriptions. Embodiments can support community intelligence applications to enable buyer computers to query and obtain lists of suppliers corresponding to categories and to generate graphs or charts that aggregate historic invoice data based on canonical category values that have been determined for suppliers.

Abstract: Input data provides an order of a quantity of finished goods to a site. Software is programmed for: accessing data defining an architecture of the supply chain network with sites, and a location of each site; enumerating one or more path solutions along the supply chain network to fulfill the order, each path solution comprising path fragments connecting two sites, a path fragment defining movement of a sub-quantity of the finished goods or raw materials; determining a cost associated with each of the plurality of path fragments, the cost comprising a duty rate, the duty rate associated with a particular path fragment based on the locations of the two sites connected by the particular path fragment and the sub-quantity of the finished goods or finished goods raw materials moved between the two sites; determining one or more optimal path solutions; and outputting the optimal path solutions for display.

Abstract: Techniques for community-based spend analysis in a software-as-a-service computing environment are disclosed. For example, embodiments disclose a method that may include receiving, at a spend management computer system (SMCS) instance of a region, a request for one or more optimization recommendations. The method may include analyzing, by the SMCS instance of the region, spend data, and determining, based on the analyzed spend data, community-based spend comparison information. The method may include causing display of a graphical user interface (GUI) that includes the community-based spend comparison information, and causing displaying in the GUI of one or more filtering options configured to filter the spend comparison information. The method may further include, in response to the request for one or more optimization recommendations, causing displaying in the GUI of a recommendation associated with the community-based spend comparison information.

Abstract: A method and apparatus for facilitating the utilization of virtual payment card data is provided. In various embodiments, virtual payment card data is received by a centralized e-procurement service directly from buyer or issuer entities participating in the service. In various embodiments, secure processes protect the security of virtual payment card data on the centralized service by actively monitoring the service for abnormal view and access behaviors of the virtual payment card data. In various embodiments, viewing interfaces for the e-procurement service are actively and responsively altered to ensure secure utilization of the virtual payment card data. In various embodiments, preventive actions are taken to actively alter virtual payment card data or access methods for entities utilizing the e-procurement service to protect the integrity and security of virtual payment card data.

Abstract: One computer-implemented method comprises receiving requests to create subforms associated with a digitally stored expense trip preapproval form; in a particular subform, receiving input specifying input values for attributes of the particular subform, the plurality of input values collectively specifying the travel expense item; programmatically transmitting, to a price modeling server, a query comprising the input values and requesting a cost value for a travel item corresponding to the input values, and receiving a predicted cost of the travel expense item; automatically updating the particular subform to display the predicted cost and to populate the predicted cost into a total cost attribute, the total cost attribute being separate from the predicted cost; receiving an updated value of the total cost attribute and updating it; in response to determining that the updated total cost attribute differs from the predicted cost, presenting a notification specifying an amount of the difference.

Abstract: Techniques are disclosed for improving spend approval cycle time in a software-as-service (SasS) electronic spend management system based on community spend approval information. The techniques include the spend management system collecting information about spend approval cycle times across a community of users that use the system. A graphical user interface is then provided by the spend management system to individual customer users of the spend management system where the graphical user interface includes a graphical comparison of the user's individual spend approval cycle time performance against the community's spend approval cycle time performance. By doing so, the individual user can be motivated to improve or maintain his or her spend approval cycle time performance.

Abstract: A computer-implemented method is disclosed. The method includes obtaining, by a de-duplication server, a candidate pair of a plurality of digitally stored documents from a document database. Text elements are identified from each digitally stored document in the candidate pair in response, and the text elements are stored as document extraction attributes. The method then automatically computes and stores relative positional differences of the text elements between each digitally stored document of the candidate pair and a document similarity score based on the relative positional differences. The relative positional differences are compared with a similarity function to form a difference similarity vector for the candidate pair. The difference similarity vector comprises components corresponding to each relative positional difference. The components of the difference similarity vector are aggregated to determine a final score for the candidate pair.

Abstract: In one embodiment, the disclosure provides a machine-implemented technique that improves the traditional methods of expense reimbursement processes by allowing an authorized delegate, e.g., administrative assistant, that is acting on behalf of another, e.g., account owner, to add expense items through a device on which the delegate is logged-in to, as opposed to a device on which the account owner is logged-in to, all without requiring the delegate to manage multiple user accounts and in an automated fashion.