Credit scoring method based on hyper-parameter optimization

Abstract

The invention relates to a credit scoring method based on hyper-parameter optimization, and the method comprises the steps: S1, collecting scoring main body information data, carrying out the preprocessing and feature selection of the data, and making a training data set and a test data set; S2, establishing a credit scoring model, selecting an XGBoost algorithm for modeling, and optimizing hyper-parameters of the algorithm by combining a Gaussian process with Bayesian; S3, selecting an optimal hyper-parameter set to fix an XGBoost algorithm, and training a credit scoring model by using the training data set; and S4, predicting and evaluating the credit scoring model by adopting the test data set, and calculating a credit score through a formula score = A-B * ln (p / (1-p)). According to theinvention, the hyper-parameters are optimized; when the target function curve cannot be determined, through conjecture hypothesis, it is determined that the target function meets multivariable Gaussian distribution, and the hypothesis evaluation model is further corrected, so that the efficiency and reliability of hyper-parameter optimization are improved, the model generation efficiency is improved, the enterprise model replacement efficiency is improved, and the risk control capability is improved.

Description

technical field [0001] The invention relates to the technical field of computer credit scoring, in particular to a credit scoring method based on hyperparameter optimization. Background technique [0002] With the rapid development of the Internet credit industry, risk issues are also emerging. Using models to control risk issues has become the preferred solution for many companies. Using models for credit evaluation can greatly improve approval efficiency and save labor costs. [0003] During the modeling process, the adjustment of model hyperparameters takes a lot of time. Usually, the methods of parameter optimization include network search method and random search method. The network search method cannot be applied to continuous parameters. Once the scale of the parameter combination increases, it will increase exponentially during the traversal process and consume a lot of time. Random search cannot use prior knowledge for the selection of the next set of hyperparamete...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a credit scoring method based on hyperparameter optimization, which aims to solve the problem that it takes a lot of time to adjust the model hyperparameters in the modeling process

Images