Model interpretable method for detecting interaction characteristics in financial risk control field

Abstract

The invention discloses a model interpretability method for detecting interaction characteristics in the financial risk control field, and relates to the field of graph neural network technology and model interpretability, and the method comprises the following steps: 1, training an additive model according to the existing training characteristics and training labels; step 2, using an interaction feature detection module to detect an existing interaction feature pair, using the obtained interaction feature pair, the training label and the residual error in the step 1 to construct a GAM model, and adding the additive model and the GAM model to obtain a GAM2 model containing the interaction feature pair; 3, according to the principle that when high-order interaction exists and only when all low-order interaction exists, multi-round iteration is conducted on the GAM2 model till the interaction feature order of a certain round of iteration is not increased any more, and a GAMn model is obtained; and step 4, realizing visualization and report export.

Description

technical field [0001] The invention relates to the field of graph neural network technology and model interpretability, in particular to a model interpretable method for detecting interactive features in the field of financial risk control. Background technique [0002] In recent years, the new generation of artificial intelligence technology with machine learning (Machine Learning), especially deep learning (DeepLearning) as the beacon, has been developing in a more advanced, complex and autonomous direction, bringing new changes to economic and social development. opportunity. The application of AI has led to a "species explosion", which has increasingly penetrated into all walks of life and all aspects of human life, and is expected to shape new economic and social forms. At the same time, science and technology ethics has increasingly become a "must-have" in current AI technology development and industrial applications, and all walks of life have been exploring the eth...

AI Technical Summary

Problems solved by technology

[0019] 3. If the model does not correctly model the causal relationship, since the interpretable method directly explains the model, there is a lack of early testing of the correctness of the model modeling

[0020] 4. If the parameter setting of the interpretation method is incorrect, the parameter setting will affect the interpretation result, and the stability of the parameter will directly affect the credibility of the interpretability

Images