Advances, Applications, and Challenges of Federated Learning Technologies in the Financial Domain

Abstract

Through inquiry and discussion of various literatures, the current application status of federated learning technology in the financial field and the challenges it faces are analyzed. Federated learning technology is based on the concept of distributed learning and has been applied in anti-fraud, risk management, stock recommendation and other financial fields, and has achieved certain results. However, federated learning still faces many challenges in the financial field due to issues such as data heterogeneity, privacy protection, and model fusion. Future research directions include improving model fusion algorithms and improving security and privacy protection technologies.