Coupa Software Inc.

Scott Harris

Ahmad Sadeddin

Vincent Toesca

Justin Mahen Mehta

Andrew Miller

Dmitri Korobov

Donna Wilczek

Tushar Rawal

Prasanna Kumar

Amit Vijayant

Snigdha Dharmavaram

Steve Deol

Maggie Mae Joy

Yutaka Hosoai

Benjamin J Kwitek

Jeffrey Hellman

Sandeep Damodar Bhide

Charles E Jennings

Christopher Yin

Joshua Danielson

Yao Yao

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.

Community-based data analysis in a software-as-a-service system using a deep learning classifier

A vehicle monitoring system that monitors operation of a first vehicle on a road to determine an amount of fuel actually used by the first vehicle on each of a plurality of stretches of the road, and to use that amount of fuel used by the first vehicle on stretches of the road to determine an estimated range that a vehicle can travel based on a current fuel amount of the vehicle. The fuel is preferably electric charge. An embodiment crowd-shares the data between vehicles, so that a vehicle can get information about the battery consumption on an actual stretch of roadway.

Electric vehicle range detection and processing

In an embodiment, a computer-implemented method comprises receiving supplier invoice data comprising one or more supplier payment objects corresponding to a supplier to a customer of a supplier-customer transaction. A match determination is made between the supplier payment object and a verified payment object. In response to a no-match determination, a customer transaction system is queried to validate the supplier, and in response to the supplier validation, a validation payment object is created, validating the supplier. A match determination is made between the supplier payment object and the verified payment object, and the supplier invoice is automatically generated. In response to receiving subsequent supplier invoice data corresponding to the supplier of subsequent supplier-client transactions, for each subsequent supplier-client transaction, the subsequent supplier invoice is automatically generated with the verified payment object.

Automatic synchronization of payment data across distributed systems

A Natural Language Command system, which receives Natural Language Commands either over a voice system or over a text system. The commands are associated with the session, and thus can be modified.

Natural language recognition assistant which handles information in data sessions

Techniques for community-based spend analysis in a software as a service computing environment are disclosed. The techniques leverage information available about community spend to provide new insights into a particular customer's spend. The new insights result from receiving a request for an optimization recommendation, importing spend data comprising a plurality of spend data lines, and using a trained deep learning classifier to classify the spend data lines in a set of standard spend categories to compute a first and second aggregate of monetary amounts. An optimization recommendation is sent to the customer based on a comparison of the first and second aggregate of monetary amounts is sent to a particular customer.

Systems and methods for obtaining required information prior to initiation of a transaction are described herein. In an embodiment, a system stores entity data defining a plurality of entities and data record requirement data identifying one or more required data record fields for one or more transactions. The system receives a request to initiate a transaction from a first client computing device corresponding to an account of a first entity. The system subsequently receives a request to view or participate in the particular transaction from a second client computing device corresponding to an account of a second entity. The system determines that the second entity has not provided data for the one or more required data record fields and, in response, restricts the second client computing device from viewing or participating in the transaction until the second entity has provided the data for the one or more required data record fields.

Restricting access to transactions based on information requirements

A fraud detection system for detecting fraudulent acts related to payment discounts from digital transactional data is disclosed. In some embodiments, the fraud detection system is programmed or configured with data structures and/or database records that are arranged to detect an occurrence of a triggering event, such as receiving an early payment discount by a buyer account from a supplier account. The fraud detection system is programmed to analyze how a first amount charged for certain items by the supplier account to the buyer account before the triggering event has changed to a second amount after the triggering event from digital documents related to procurement transactions. The certain items may include items for sale or for other miscellaneous items. The digital documents may include catalogs, purchase requisitions, purchase orders, or invoices. The fraud detection system is programmed to further detect any potential fraud committed by the supplier account based on the analysis result. Finally, the fraud detection system is programmed to send a warning of the potential fraud to other buyer accounts that have been offered promotions, such as the early payment discounts, from the supplier account.

Detecting supplier fraud from digital transactional data

In an embodiment, a system and method for the following steps are described herein: receiving transactional data describing transactions between multiple computing devices, using the transactional data, identifying multiple instances of a particular event type, each instance comprising multiple transactions associated with a particular computing device, using the transactional data related to the multiple instances of the particular event type, determining multiple items for the particular event type, receiving, from a client computing device, an event generation request for an event of the particular event type, generating an event template identifying one or more of the multiple items associated with the particular event type, and displaying, through a graphical user interface executing on the client computing device, the event template.

Using transaction data to identify computing devices capable of performing transactions subject to transaction parameters

A method and apparatus for generating recommendation data for cataloging items in an e-procurement system is provided. In various embodiments, a database of records is created and maintained corresponding to a plurality of transactions in an e-procurement system. In various embodiments, database records are weighted and sorted according a transaction method associated with the records. In various embodiments, recommendation data is generated for items associated with the records to suggest more efficient methods for offering items for procurement in an e-marketplace based on the weights and sort order of the records.

Catalog enablement data for supplier systems based on community activities

This application discloses systems, methods, and computer products related to generation, analysis, and transmission of multiple types of data among multiple computers within a networked computer environment. The disclosed approaches further enable integration of different types of data, notification of availability of certain types of data, and coordination of communication of specific types of data.

Management of payment plan data in a distributed environment

A computer implemented method maintaining a database including records of one or more supplier system catalogs enabled by multiple buyer systems. The method includes tracking, by the processor, query expressions and corresponding query results generated from the database by a specific buyer system, the query results identifying matches between the query expressions and a set of records of supplier system catalogs enabled and integrated for procurement with the specific buyer system. The method further includes determining, from the query expressions and corresponding query results, the query expressions that satisfy criteria for low match rates and identifying additional matches between the query expressions and at least one unassociated supplier system catalog outside of the set of enabled and integrated supplier system catalogs, the identifying based upon an analysis of community buyer system data. A report is generated based upon the additional matches and transmitted to the specific buyer system.

Generating reports with recommendations for enabling supplier catalogs based on procurement data from buyer community

Techniques for implementing conditional approval chains through a spend management system are described herein. In an embodiment, a spend management system stores data defining a plurality of conditional approval chains. The system receives a request to perform a particular transaction between a first account and a second account. The system identifies a particular conditional approval chain, of the plurality of conditional approval chains, for the transaction, the particular conditional approval chain comprising a particular condition based on a particular rating value for a particular account and a consequent comprising a requirement for approval from a third account. Using the particular rating value for the second account, the system computes a result of the particular conditional approval chain. Based on the computed result of the particular conditional approval chain, the system determines that the transaction requires approval from the third account and, in response, the system sends a request for approval of the transaction to a client computing device associated with the third account.

Integrating tracked transaction data into approval chains for digital transactions

Techniques and a system are provided for generating correlations based on inferred behavior by an inferred event detection system executing on a mobile computing device. Inferred events are events that are detected without an explicit input to the mobile computing device. The inferred events are further classified by the inferred event detection system. In one embodiment, a method comprises, using an application on a mobile computing device, wherein the mobile computing device includes at least one geolocation antenna capable of providing geolocation information that is accessible by the application and that specifies a geolocation of the mobile computing device at a particular time, monitoring the geolocation information; without receiving an explicit request to the application executing on the mobile computing device, determining by the mobile computing device at a first time, a first timestamp and a first geolocation information for the mobile computing device at the first time; without receiving an explicit request to the application executing on the mobile computing device, determining by the mobile computing device at a second time, a second timestamp and a second geolocation information for the mobile computing device at the second time; determining, based on a difference between at least one of the first timestamp and the second timestamp, or the first geolocation information and the second geolocation information, that a first event of a first monitored event class has occurred between the first time and the second time; generating, based on the first monitored event class and in response to determining the first event has occurred after the second time, a first alert on the mobile computing device, wherein the first alert comprises a prompt for additional information to be associated with the first event; causing to be stored at a computer system, information about the first event including the first monitored event class and any additional information associated with the first event that is received in response to the first alert.

Growing community of inventors

Menlo Park, CA, United States of America

Scott Harris