Fraud detecting and risk assessing method and system, equipment and storage medium

Abstract

The invention provides a fraud detecting and risk assessing method and system, equipment and a computer-readable storage medium. The method comprises the following steps of: collecting original data of a client user; extracting characteristic data from the original data by utilizing a data processing algorithm; inputting the characteristic data into a pre-trained machine learning model matched with the characteristic data, generating a model output result and uploading the model output result to a server; and outputting a fraud detecting and risk assessing result by utilizing a risk control decision engine and in combination with the model output result and historical data and third party data associated with the client user. By utilizing the method provided by the invention, the computingcapacity of client equipment can be fully utilized to reduce the computing pressure on the server; and a client does not need to upload the original data to the server, so that the data transmissionpressure between the client and the server and the risk of the leakage of privacy data and security information of the user can also be reduced.

Description

technical field [0001] The present invention relates to the technical field of information processing, in particular to a fraud detection and risk assessment method, system, device and storage medium. Background technique [0002] Traditional big data applications rely on cloud computing (Cloud Computing), that is, collect data on the client side, and then upload it to a centralized cloud server, use big data technology to perform machine learning, obtain models or form intelligent inferences, and thus perform fraud detection and risk assessment, such as solving special anti-fraud and risk assessment issues in the field of Internet finance. However, such techniques have several problems that are currently difficult to solve: [0003] 1. The cloud server has to process the massive data generated by the client, which will incur high transmission and computing costs. [0004] 2. Limited by network bandwidth and delay, it is not suitable for real-time applications with high us...

AI Technical Summary

Problems solved by technology

However, such techniques have several problems that are currently difficult to solve:

[0003] 1. The cloud server has to process the massive data generated by the client, which will incur high transmission and computing costs

[0004] 2. Limited by network bandwidth and delay, it is not suitable for real-time applications with high user experience requirements

Images