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: A computer-implemented method for detecting and managing duplicate invoices is provided. In one embodiment, the method includes accessing, in a digital storage device, invoices associated with a buyer computer. Candidate invoices having similar attributes are identified from the invoices and nodes representing the candidate invoices are created and stored in computer memory. At least two of the candidate invoices are determined likely to be duplicate invoices and an edge is generated between nodes representing the at least two candidate invoices, indicating that the at least two candidate invoices are likely to be duplicate invoices. A set of filters is programmatically applied using the at least two candidate invoices as inputs. The at least two candidate invoices are determined to be duplicate invoices based on an output of the set of filters and a notification is sent to the buyer computer indicating that the at least two candidate invoices are duplicate invoices.

Abstract: A computer-implemented method for detecting and managing duplicate invoices is provided. The method includes accessing, in a digital storage device, invoices associated with a buyer computer. Candidate invoices having similar attributes are identified from the invoices and nodes representing the candidate invoices are created and stored in computer memory. At least two of the candidate invoices are determined likely to be duplicate invoices and an edge is generated between nodes representing the at least two candidate invoices, indicating that the at least two candidate invoices are likely to be duplicate invoices. A set of filters is programmatically applied using the at least two candidate invoices as inputs. The at least two candidate invoices are determined to be duplicate invoices based on an output of the set of filters and a notification is sent to the buyer computer indicating that the at least two candidate invoices are duplicate invoices.

Abstract: Computer-implemented techniques for repeatable and interpretable divisive analysis. In one embodiment, for example, a method comprises: identifying top-level cohorts of data items based on one or more characteristics of the data items in common; recursively or iteratively dividing a selected top-level cohort in a top-down manner resulting in a plurality of sub-level cohorts arranged in a hierarchy; detecting a particular data item that is a statistical outlier among data items of a leaf cohort in the hierarchy; and causing display of an indication in a computer user interface that the particular data item is an outlier.

Abstract: Systems and methods for improving a computing system comparing past post-approved transaction records to past pre-approved transaction records are described herein. In an embodiment, a server stores a first plurality of digital electronic records identifying a plurality of past post-approved transactions by a first entity and a second plurality of digital electronic records for the first entity identifying a plurality of past pre-approved transactions by the first entity. The server uses a first machine learning system to determine that a subset of the first plurality of digital electronic records which identify a subset of the plurality of past post-approved transactions correspond to one or more pre-identified categories and a second machine learning system to match one or more particular digital electronic records of the subset of the first plurality of digital electronic records with one or more records of the second plurality of digital electronic records.

Abstract: Computer-implemented techniques for repeatable and interpretable divisive analysis. In one embodiment, for example, a method comprises: identifying top-level cohorts of data items based on one or more characteristics of the data items in common; recursively or iteratively dividing a selected top-level cohort in a top-down manner resulting in a plurality of sub-level cohorts arranged in a hierarchy; detecting a particular data item that is a statistical outlier among data items of a leaf cohort in the hierarchy; and causing display of an indication in a computer user interface that the particular data item is an outlier.

Abstract: Systems and methods for improving a computing system comparing past post-approved transaction records to past pre-approved transaction records are described herein. In an embodiment, a server stores a first plurality of digital electronic records identifying a plurality of past post-approved transactions by a first entity and a second plurality of digital electronic records for the first entity identifying a plurality of past pre-approved transactions by the first entity. The server uses a first machine learning system to determine that a subset of the first plurality of digital electronic records which identify a subset of the plurality of past post-approved transactions correspond to one or more pre-identified categories and a second machine learning system to match one or more particular digital electronic records of the subset of the first plurality of digital electronic records with one or more records of the second plurality of digital electronic records.

Abstract: A computer-implemented method of executing a programmed spend management computer system. The computer system comprises a data pre-processor that is communicatively coupled to a plurality of the application instances and accesses historic transaction data from any of the instances and thereby has access to a large community of data across all tenants. The data pre-processor is programmed to normalize transaction descriptions and determine line spend values, unit price values, quantity values, and buyer country data for a plurality of commodities, and to store the data in item sets in digital storage. A statistical processor is coupled to the digital storage to access the item sets and executes statistical calculation on the item sets to generate pricing insight data. Pricing insights and/or prescriptions are generated automatically under stored program control and provided to a presentation processor for output to and/or rendering to an end-user device.

Abstract: A computer-implemented method for detecting and managing duplicate invoices is provided. The method includes accessing, in a digital storage device, invoices associated with a buyer computer. Candidate invoices having similar attributes are identified from the invoices and nodes representing the candidate invoices are created and stored in computer memory. At least two of the candidate invoices are determined likely to be duplicate invoices and an edge is generated between nodes representing the at least two candidate invoices, indicating that the at least two candidate invoices are likely to be duplicate invoices. A set of filters is programmatically applied using the at least two candidate invoices as inputs. The at least two candidate invoices are determined to be duplicate invoices based on an output of the set of filters and a notification is sent to the buyer computer indicating that the at least two candidate invoices are duplicate invoices.

Abstract: Systems and methods for improving a computing system comparing past post-approved transaction records to past pre-approved transaction records are described herein. In an embodiment, a server stores a first plurality of digital electronic records identifying a plurality of past post-approved transactions by a first entity and a second plurality of digital electronic records for the first entity identifying a plurality of past pre-approved transactions by the first entity. The server uses a first machine learning system to determine that a subset of the first plurality of digital electronic records which identify a subset of the plurality of past post-approved transactions correspond to one or more pre-identified categories and a second machine learning system to match one or more particular digital electronic records of the subset of the first plurality of digital electronic records with one or more records of the second plurality of digital electronic records.

Abstract: Computer-implemented techniques for repeatable and interpretable divisive analysis. In one embodiment, for example, a method comprises: identifying top-level cohorts of data items based on one or more characteristics of the data items in common; recursively or iteratively dividing a selected top-level cohort in a top-down manner resulting in a plurality of sub-level cohorts arranged in a hierarchy; detecting a particular data item that is a statistical outlier among data items of a leaf cohort in the hierarchy; and causing display of an indication in a computer user interface that the particular data item is an outlier.