Big data risk control model and online system configuration technology

Abstract

The invention provides a big data risk control model and online system configuration technology, which comprises risk control model construction and risk control model configuration, and is characterized in that the risk control model construction comprises the steps of sample acquisition, data processing, data table generation, data division, feature engineering and model establishment, wherein the model configuration comprises feature configuration, model configuration and monitoring configuration. By implementing the technical scheme of the invention, on one hand, a plurality of feature construction modes are combined together, and a variable cross combination operation mode is added, so that the combination relationship between variables is comprehensively mined, and the model precision is improved; on the other hand, on the basis of traditional feature screening, correlation inspection between variables is added, so that excessive variables entering the model can be prevented, thecalculation cost can be prevented from being increased, and model over-fitting can also be prevented; projects, characteristic variables, models, user roles and the like can be managed in a unified mode.

Description

technical field [0001] The invention relates to the field of financial risk control model technology and model online configuration theory, in particular to a big data risk control model and online system configuration technology. Background technique [0002] Financial risk control refers to the measures and methods adopted by risk managers in order to reduce or eliminate various possible risk events in the financial transaction process or reduce the losses caused by risk events, so financial risk control is an important link in the financial transaction process . [0003] The traditional financial risk control process is generally divided into the following steps: the first step, data modeling: the modeler retrieves data from the database, performs data cleaning, and performs modeling work; the second step, deploys the model to the system: the developer will Variable rules, model rules, and monitoring rules are written and deployed to the system for testing; the third ste...

AI Technical Summary

Problems solved by technology

[0004] Traditional financial risk control has the following disadvantages: 1. The method of using WOE transformation in the feature engineering of the traditional risk control model, and then using the Logistic model to fit and construct the feature engineering method has been unable to keep up with the development speed of big data, the Internet, and machine learning; 2. In traditional financial risk control, model deployment requires modelers to write variable rules, model rules, and monitoring rules into written materials and hand them over to developers. Developers deploy these to the system, and developers and models communication, testing

This method not only increases the cost of communication, but also may cause many problems in the test due to insufficient communication, and because the test also requires developers to cooperate with the test, it also consumes manpower and time, and increases the cost of the project.

Images