Credit line determination method and device based on machine learning and equipment fingerprints

Abstract

The invention provides a credit line determination method and device based on machine learning and equipment fingerprints. The method comprises the following steps: obtaining a unified credit requestof a target client; according to the unified credit granting request, obtaining operation data and a knowledge graph of a target client; determining industry data of a target customer according to theknowledge graph; importing the operation data and the industry data into a trained machine learning model, and obtaining an operation score of a target customer; and determining the admission and credit limit of the target customer according to the operation score. According to the method, the enterprises are subjected to industry classification and classification, categories are set in industryclassification, the operation levels of the enterprises in the industry categories are determined, multi-dimensional evaluation of the enterprises is realized, historical change description of operation data is performed according to a machine learning model, and the future operation conditions of the enterprises are predicted.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a method and device for determining a credit limit based on machine learning and device fingerprints. Background technique [0002] In B2B e-commerce, in order to solve the shortage of funds faced by small and medium-sized enterprises, e-commerce platforms can provide order financing for small and medium-sized enterprises through docking with banks, and solve the funds needed for the business turnover of small and medium-sized enterprises. Among them, order financing refers to the company's creditworthy buyer's product order, under the conditions of mature technology, guaranteed production capacity and effective guarantee, the bank provides special loans for the company to purchase materials and organize production. Immediately after repaying the business of the loan. [0003] Enterprises in supply chain finance are greatly affected by the industry, and each industry h...

AI Technical Summary

Problems solved by technology

However, the current bank order financing system only selects high-quality enterprises with good operating conditions for lending, and refuses to lend to enterprises with poor short-term operating conditions. The degree of intelligence is low and it is impossible to predict the future operating conditions of enterprises.

Moreover, the current bank's order financing system lacks an effective false order inspection function, and there is a risk of fraudulent transactions

Images