Pre-loan credit evaluation method and device

Abstract

The invention discloses a pre-loan credit evaluation method and device. The method comprises the following steps: obtaining client account information, loan blacklist user information and loan whitelist user information of a plurality of banking institutions; abnormal data cleaning is carried out on the client account information, the loan blacklist user information and the loan whitelist user information of the multiple banking institutions; constructing a training sample set according to the client account information, the loan blacklist user information and the loan whitelist user information of the plurality of banking institutions after abnormal data cleaning; training the pre-loan credit evaluation model according to the training sample set to obtain a trained pre-loan credit evaluation model; and performing pre-loan credit evaluation by using the trained pre-loan credit evaluation model. According to the invention, data combination of multiple bank institutions can be realized,the performance of the pre-loan credit evaluation model is improved, leakage of private data of users is avoided, supervision is facilitated, and the risk of data violation is reduced.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a pre-loan credit evaluation method and device. Background technique [0002] With the development of machine learning and artificial intelligence, the application of machine learning in the field of commercial bank loan credit evaluation is currently a direction of exploration. However, machine learning requires a large amount of data as the basis for learning. The data of each commercial bank is limited. It is difficult to train high-quality machine models only relying on the data of commercial banks themselves. If the data of other banking institutions are combined for training, the privacy of user data of each banking institution will be leaked. [0003] Specifically, when the existing technology uses machine learning algorithms for loan credit evaluation, it generally collects data from multiple institutions and uses machine learning algorithm models for loan credit evalu...

AI Technical Summary

Problems solved by technology

[0003] Specifically, when the existing technology uses machine learning algorithms for loan credit evaluation, it generally collects data from multiple institutions and uses machine learning algorithm models for loan credit evaluation. Such a method will leak the user's private data and make supervision difficult. Increased data breach risk

Images