Model interpretation method and device based on cooperative game, and electronic equipment

Abstract

Embodiments of the invention provide a model interpretation method and a device based on cooperative game, and electronic equipment, the method is applied to the electronic equipment, and the electronic equipment comprises a trained machine learning model for prediction or classification. The method comprises calculating a contribution value of each target feature selected from a plurality of features in at least one input test sample to the output result according to the output result of the machine learning model, so as to explain the output result of the machine learning model according tothe contribution value of each selected target feature to the output result. According to the method, a machine learning model is combined with a cooperative game theory, and a prediction result of the machine learning model is explained by calculating contribution degree values of target features, including a nonlinear model and a linear model. Meanwhile, the method can achieve the interpretationof the machine learning model for a single target feature, and also can achieve the interpretation of the overall prediction result of the machine learning model.

Description

technical field [0001] The present application relates to the technical field of machine learning, and in particular, relates to a cooperative game-based model interpretation method, device, and electronic equipment. Background technique [0002] With the development of big data and artificial intelligence, machine learning technology has been more and more widely used, but most of the current machine learning models are black-box algorithms, and only the calculation results of the machine learning model can be obtained, and it is impossible to determine whether the calculation results are Accurate, which brings up the issue of confidence in machine learning models. Especially in the financial or medical industries, there is an increasing requirement for machine learning models to be interpretable. [0003] At present, although models such as decision trees and logistic regression algorithms are interpretable, such models are linear models and have certain limitations. In ...

AI Technical Summary

Problems solved by technology

[0003] At present, although models such as decision trees and logistic regression algorithms are interpretable, such models are linear models and have certain limitations

In addition, there are also technologies that use the LIME (Local Interpretable Model-Agnostic Explanations) algorithm to explain the machine learning model, but the LIME algorithm randomly samples near each prediction sample to generate new prediction samples and new prediction results, so that according to the new prediction results Explain the machine learning model, but because the random sampling method is uncontrollable, there is no guarantee that the LIME algorithm is still effective in complex scenarios

In addition, the above two methods are to explain the machine learning model as a whole, and cannot explain the role of a single feature

Images