Enterprise financial service risk prediction method and device

Abstract

The embodiment of the invention provides an enterprise financial service risk prediction method and device, which can be used in the technical field of artificial intelligence, and the method comprises the steps that the operation state information of a target enterprise which is not authorized by a financial service at present is input into a financial service risk prediction model to obtain a financial service risk prediction level, whether to provide the financial service to the target enterprise is determined based on the financial service risk prediction level; the financial service risk prediction model is obtained after multiple enterprises are scored by applying a fusion model in advance, the fusion model is obtained based on a marking model and historical enterprise data with unknown labels, and the marking model is obtained through training based on historical enterprise data with known labels processed in a transfer learning mode and a resampling mode. The accuracy and reliability of the financial service risk prediction process of the target enterprise without financial service authorization of the target financial institution can be effectively improved, and the pertinence and effectiveness of the financial institution for providing the financial service for the enterprise can be improved.

Description

technical field [0001] This application relates to the technical field of data processing, in particular to the technical field of artificial intelligence, and in particular to a method and device for risk prediction of corporate financial services. Background technique [0002] The existing bank rating indicators mainly consider large and medium-sized enterprises. Although they have a certain coverage rate for small and micro enterprises, as the importance of financial services to the public is further enhanced, the customer base is declining, and banks need to serve more existing evaluations. Small and micro enterprises that cannot be covered by the system. However, the status quo of small enterprises determines the characteristics of its difficult risk assessment. [0003] At present, compared with expert rules, the existing method of applying machine learning models to enterprise risk prediction can reduce labor costs, but a successful model needs to rely on a large amo...

AI Technical Summary

Problems solved by technology

[0003] At present, compared with expert rules, the existing method of applying machine learning models to enterprise risk prediction can reduce labor costs, but a successful model needs to rely on a large amount of data annotation training, and the small and micro enterprise customers that banks have served It cannot cover all small businesses, and it is impossible to score all small businesses through expert evaluation. If the original unlabeled small and micro enterprise labels are obtained through weak supervision, there are hundreds of thousands of small and micro customer samples and labels in the bank. , and there are tens of millions of unlabeled small and micro enterprises outside the bank. Therefore, there is an uneven distribution of labels derived from the weak supervision method. That is to say, the existing enterprise financial service risk prediction method for small and micro enterprises, Its prediction accuracy is limited, and it cannot meet the financial risk prediction accuracy requirements of banks and other financial institutions for various enterprises (especially small and micro enterprises)

Images