Intelligent evolutionary pre-credit system

Abstract

The invention belongs to the technical field of credit fusion services, and particularly relates to an intelligent evolutionary pre-credit-granting system which comprises a feature extraction center,a feature library, a model training center, a model library, a model operation center and an intelligent auxiliary management system. The feature extraction center comprises a credit unit definition module, a data preprocessing module, a data vectorization module and a feature processing module; wherein the feature library is the basic data support of the model training center and the model operation center; the model training center comprises a model training and verification module and a model self-evolution module; wherein the model library provides model support for the model operation center, and the model operation center comprises an enterprise pre-credit module and a personal pre-credit module; the intelligent auxiliary management system carries out inference, artificial participation control, authority control, automatic alarm and the like on input data by monitoring program running logs and data flow conditions, and controls the relationship among all centers.

Description

technical field [0001] The invention belongs to the technical field of financial credit services, and in particular relates to an intelligent evolutionary pre-credit system. Background technique [0002] Today's society is a rapidly developing society, with advanced technology, information flow, people's communication is getting closer and closer, and life is becoming more and more convenient. With the continuous integration of technologies such as the Internet of Things, social networks, and cloud computing into our lives and With the rapid development of existing computing power, storage space, and network bandwidth, the data accumulated by humans continues to grow and accumulate in many fields such as the Internet, communications, finance, commerce, and medical care. With the continuous growth of stored data, people use the data in ever-changing directions and methods, which make fully automatic intelligent credit possible. [0003] With the changes in people's consumpti...

AI Technical Summary

Problems solved by technology

[0007] 1. The data acquisition is biased. The main data source of each merchant in the Internet credit investigation process is the merchant’s original underlying data, which relies on the merchant’s original business, and the coverage is incomplete. The biased data leads to increased credit risk or loss of opportunities;

[0008] 2. The lack of data is serious. Internet credit investigation requires the collection of a large amount of data for analysis in the early stage. It is very difficult to obtain the data of the demand side or the data obtained is insufficient, so it is impossible to give a good credit strategy;

[0009] 3. Starting from the perspective of entities, ignoring some relationship characteristics, the current credit investigation methods generally start from the perspective of individual entities or business entities, thus ignoring the relationship between groups, resulting in biased results;

[0010] 4. Lack of model evolution mechanism. The credit policy itself is to understand users through user information, hoping to give a reasonable credit value, while the demand side hopes that the higher the credit value, the better, and may study the loopholes in the credit policy to improve its credit value , resulting in increased credit risk

Images