Credit risk control system and method based on federation mode

Abstract

The invention relates to a big data technology, and aims to provide a credit risk control system and method based on a federation mode. The system comprises a heterogeneous data access layer used foraccessing and converting data, a data preprocessing layer used for preprocessing original data, and a sample alignment layer used for keeping training samples of different data providers aligned, anda federated learning layer used for training a local model by utilizing the participant local data and forming a global model after gradient aggregation. The invention provides a unified data access format, data preprocessing and a risk prediction model based on federated learning, and solves the challenge problem brought by data heterogeneity and privacy leakage to risk control. A central serverdoes not need to participate in the model training and learning process, and it can be guaranteed that user privacy is not eavesdropped. Risk control modeling can be carried out by combining a plurality of different participants, the modeling process is standardized, the risk control capability is finally improved, and the cost is reduced for enterprises.

Description

technical field [0001] The invention relates to big data technology, specifically a credit risk control system and method based on the federal model, which is the application of big data technology in the credit loan branch of the financial field, and is especially suitable for enterprises to carry out pre-loan risk control processes. Background technique [0002] In the pan-financial field, risk control related to credit business is one of the core links that almost all financial companies are most concerned about. However, the traditional credit risk control method requires a large number of manual (review specialists) participation, and at the same time has a high risk of privacy disclosure, human manipulation and user fraud. For example, in the traditional risk control method, the collection method of user data is mainly provided by the applicant himself, and then the approval agency manually verifies the accuracy of the information, and finally credits the applicant acc...

AI Technical Summary

Problems solved by technology

However, none of these methods take into account the privacy protection of user data during multi-party joint modeling.

Images