Fidelity Information Services, LLC

Matthew Petersen

Benjamin Wellmann

David Berglund

Lauren Morrison

Jeffrey Paul Kubler

Shane Saunders

Eric Bond

David Raynault

Philip J Ponsaran

Joe Leung

Daniel Wakeman

Zachary Jasinski

Joseph Fredric Sutthoff

Disclosed herein are systems and methods for managing transaction disputes. Techniques include accessing a transaction pattern model associated with a user account; detecting deviation of a transaction from the transaction pattern model; transmitting, based on the detected deviation, transaction data to a user device; receiving an input at the user device in response to the transmitted data; generating, based on the received input, dispute data; storing the dispute data; monitoring data extracts associated with the user account; detecting, based on the monitoring, a data extract indicating a posted state of a transaction associated with the dispute data; and updating the dispute data based on the data extract indicating the posted state.

Systems and methods to manage transaction disputes using predictions based on anomalous data

Systems and methods for activity risk management are disclosed. A system for activity risk management may include a memory storing instructions and at least one processor configured to execute instructions to perform operations including: accessing document data associated with at least one of a transaction or an individual; normalizing the document data; classifying the normalized document data; extracting model input data from the classified document data; applying a machine learning model to the extracted model input data to score the document data, the machine learning model having been trained to generate a favorability output indicating a favorability of the transaction or individual; and generating analysis data based on the scored document data.

Systems and methods for analyzing documents using machine learning techniques

Systems and methods for entity risk management are disclosed. A system for entity risk management may include a memory storing instructions and at least one processor configured to execute instructions to perform operations including: establishing a connection between the system and a data source, the data source being remote from the system and associated with a first entity; receiving first document data from the data source; normalizing the first document data; classifying the normalized document data; extracting model input data from the classified document data; applying a machine learning model trained to predict risk levels using second document data to the extracted model input data to predict a risk level associated with the first entity; generating analysis data based on the predicted risk level; and based on the analysis data, transmitting an alert to a management device communicably connected to the system.

Systems and methods for using machine learning techniques to predict institutional risks

Growing community of inventors

Apex, NC, United States of America

Matthew Petersen