Insurance Anti-fraud based on FL-WOE Encoding for Vertical Federated Learning

In recent years, federated learning has been rapidly developing as an emerging privacy computing method. Its unique distributed computing feature enables multiple participants to collaborate on modelling while ensuring that the data remains local and only the model parameters are passed on, thus effectively preserving privacy. This characteristic has led to the gradual introduction of Federated learning into real-world engineering applications, particularly in the financial sector. Banks, insurance companies, and other financial institutions are able to integrate financial data from multiple enterprises through federated learning to effectively perform a range of important financial tasks. However, financial data usually contains a large amount of personal information, and in addition to its privacy, unprocessed character data is difficult to be directly applied to models. Therefore, how to efficiently encode and convert these data into digital features has become an important problem to be solved in federated learning. The paper introduces a WOE(Weight Of Evidence) encoding method within a vertical federated learning framework, designed to maintain label confidentiality. This approach allows unlabelled participants to leverage label information for effective character feature WOE encoding, enhancing data utility while ensuring privacy. A classification task model for insurance anti-fraud is constructed and a series of evaluation metrics are used to demonstrate the effectiveness of the proposed method compared to other unsupervised coding methods. It also verifies that federated learning can integrate multi-party data and thus improve the classification ability of anti-fraud models.