The present disclosure involves systems, software, and computer implemented methods for transaction auditing. One example method includes training at least one machine learning model to determine features that can be used to determine whether an image is an authentic image of a document or an automatically generated document image, using a training set of authentic images and a training set of automatically generated document images. A request to classify an image as either an authentic image of a document or an automatically generated document image is received. The machine learning model(s) are used to classify the image as either an authentic image of a document or an automatically generated document image, based on features included in the image that are identified by the machine learning model(s). A classification of the image is provided. The machine learning model(s) are updated based on the image and the classification of the image.

Systems, computer program products, and methods are described herein for generating pre-authorized request for conditional resource transfers within a real-time resource transfer network in response to supply chain updates. The present invention is configured to electronically receive, from a computing device of a user, a request to establish a resource transfer program within a real-time payment (RTP) network, with a third party for acquisition of an item or product; generate the resource transfer program, wherein generating further comprises generating one or more requests for resource transfers (RRTs) to be fulfilled by the user; transmit control signals configured to cause the computing device of the user to display the one or more RRTs; in response, electronically receive, from the computing device of the user, an acknowledgement of the one or more RRTs; and generate a virtual dynamic resource transfer hold pre-authorizing fulfillment.

A system, platform, computer programming product, and/or method includes providing a trained intelligent agents to predict simulated transactional activity of a simulated person; pairing a person to the trained intelligent agent based upon the transactional activity of the person; predicting, by the paired trained intelligent agent, simulated transactional activity of the simulated person for a measured period; scoring the simulated transactional activity for the measured period; scoring the transactional activity undertaken by the paired person for the measured period; determining if the score of the simulated transactional activity for the measured period is different than the score of the paired person transactional activity for the measured period; and generating, in response to determining that the score of the simulated transaction activity for the measured period is different than the score of the paired person transactional activity for the measured period, a report.

A method including receiving, at a payment-messaging system from a biller financial institution, a request comprising a public consumer token of a consumer. The consumer provided the public consumer token to a biller system of a biller for a bill payment by the consumer to the biller. The biller system provided the public consumer token to the biller financial institution. The biller financial institution maintains a biller account of the biller. The acts also can include determining a risk metric representing a risk of using the public consumer token for the bill payment. The acts additionally can include sending the risk metric from the payment-messaging system to the biller financial institution. The biller financial institution sends the risk metric to the biller system to allow the biller to determine whether to assume liability for the bill payment. The acts further can include receiving, at the payment-messaging system from the biller financial institution, an authorization message for the bill payment. The authorization message was provided to the biller financial institution by the biller system. The acts additionally can include sending the authorization message for the bill payment to a consumer financial institution, to cause the consumer financial institution to send a real-time payment message through the payment-messaging system to the biller financial institution to make funds available in real-time in the biller account for the bill payment. Other embodiments are described.

A method for fraud detection and management may include a fraud detection computer program: receiving data from a plurality of sources, each data associated with a unique identifier; normalizing the data; modeling the normalized data with a trained machine learning data model; extracting features or attributes from the modeled data; generating one or more sets of weights for the features or attributes; identifying a subset of the features or attributes indicative of fraud based on the weights; enriching the subset of the features or attributes; detecting fraud based on the enriched subset of the features or attributes; and notifying one or more subscribing institutions of a fraud event for the detected fraud based on the validated subset of the features or attributes.

Systems and methods for recruiting, counter-terrorism/security, insurance underwriting, sales and marketing improvement, decisioning financial transactions and collections, and social scoring are provided. Machine learning can assign connectivity values to other community members, including individuals, companies, products, brands, cities or neighborhoods, etc. Connectivity values may be automatically harvested from or assigned by third parties or based on the frequency and/or type of interactions between community members. Connectivity values may represent such factors as alignment, reputation within the community, degree of trust, competence at one or more skills, or compatibility with others. The degree and type of connectivity between two entities may be assessed by computing a connectivity value based upon connections between entities and relative or absolute trust, competence and/or compatibility features of the connections. Connectivity values identify best prospects (customers, hires, dates), find off-grid people, underwrite insurance, ‘decision’ loans & collections, shorten sales cycles, etc.

Provided are a system and methodology for iteratively transforming data, as between multiple sets thereof, that account for underlying data generation sources and bases. Doing so, via normalization of the data, enables uniformity of interpretation and presentation of the data no matter the machine learning model that produced the data.

One or more implementations include methods, systems, and/or devices to help protect consumers from fraudulent activity using compromised PII. For example, systems and methods can be implemented that enable the detection and prevention of consumer-focused identity theft, generates a risk score and is powered by a predictive model using machine learning techniques and tools and presents information and recommended action a user can take in reports.

Methods and systems for rule-based machine learning for precise fraud detection. One system includes an electronic processor configured to determine, via a decision tree, a first subset of datasets of an aggregate dataset collection generated using a rule-based model. The electronic processor is also configured to select a third collection of datasets, each dataset included in the third collection of datasets associated with a user characteristic associated with fraud. The electronic processor is also configured to determine, via the decision tree, a second subset of datasets of the third collection of datasets, each dataset included in the second subset of datasets associated with a second set of user characteristics associated with fraud. The electronic processor is also configured to, in response to determining that an accuracy score associated with the second set of user characteristics satisfies a threshold, generate and transmit a report for display.

Pre-staged deposit details for a deposit are received from a deposit interface and the details are linked to a code associated with a deposit bag. The code is subsequently scanned at a terminal, the pre-staged details are obtained based on the code, a lock box of the terminal is unlocked for the bag to be dropped into the lock box, a deposit transaction is processed based on the pre-staged details, and the box is locked. A real-time notification is provided within a staff interface that identifies the terminal and the transaction. The code is scanned when that bag is removed from the lock box and the pre-staged details are populated within the staff interface. Staff details are recorded for the transaction during a verification procedure. The staff details are posted to a financial institution backend system and any discrepancies between the pre-staged details and the staff deposit details are noted.