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: 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 fraud detection system for detecting fraudulent acts related to account takeover in digital transactions is disclosed. In some embodiments, the fraud detection system is programmed to detect occurrences of triggering events for account takeover fraud. The triggering events generally include changes related to the taken-over account, such access patterns, account data, or linked transactional data. In response to detecting the occurrence of one triggering event, the fraud detection system is programmed to determine whether the triggering event corresponds to potential fraud by analyzing historical triggering events and triggering events involving similar accounts. In response to identifying potential fraud, the fraud detection system is programmed to send a notification of the potential fraud to a device associated with the taken-over account before the triggering event or a device associated with an affected account engaged in a transaction with the taken-over account.

Abstract: A method and apparatus for generating search data for items in an e-procurement system is provided. In various embodiments, a digital image is created or selected and data comprising search key data is generated based on the digital image. In various embodiments, the search key data is sent to a search repository listing items in an e-procurement system. In various embodiments, search data is sorted according to received search key data to present search results relating to items corresponding to the digital image.

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: Techniques for using a graphical user interface to automatically generate expense lines from images are described herein. According to an embodiment, a server computer causes storing in a data repository, data identifying a plurality of users, the data comprising feature data extracted from one or more images of the users. The server computer receives a digital photographic image captured using a camera in a mobile computing device. The server computer identifies one or more faces in the digital photographic image and determines that the one or more faces in the digital photographic image match a particular user. The server computer generates and stores an expense line in an expense data table in the data repository, the expense line comprising an identification of the particular user.

Abstract: Techniques for using a graphical user interface to automatically generate expense lines from images are described herein. According to an embodiment, a server computer causes storing in a data repository, data identifying a plurality of users, the data comprising feature data extracted from one or more images of the users. The server computer receives a digital photographic image captured using a camera in a mobile computing device. The server computer identifies one or more faces in the digital photographic image and determines that the one or more faces in the digital photographic image match a particular user. The server computer generates and stores an expense line in an expense data table in the data repository, the expense line comprising an identification of the particular user.